Back to skill

Security audit

YouTube Playlist

Security checks for vulnerabilities and agentic risk

Overview

The playlist features fit their purpose, but the optional account-setup instructions can turn supplied text into unintended local commands.

Review the account-setup commands before use. Prefer creating an API key yourself and entering it through the runtime's secret interface. The publisher should replace literal shell substitution with structured data handling and validate verification codes as exactly six digits. Signup shares your email with TranscriptOut, stored keys persist across sessions, and transcription consumes credits. Both bundled files were reviewed; the remote service remains outside this inspection.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Tool MisuseTool Parameter Abuse, Chaining Abuse, Unsafe Defaults
  • Rogue AgentSelf-Modification, Session Persistence
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (22)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
94% confidence
Finding

The supplied command performs account registration rather than playlist retrieval or transcription. Although authentication setup can support a transcription workflow, this command specifically initiates account signup, which conflicts with the declared exclusion of account chores. The restricted configuration directory and local response storage are supporting implementation details, not separate mismatches.

Content

No source excerpt is available for this finding.

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
85% confidence
Finding

Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

Content

Scanner excerpt · references/auth-setup.md (reported line 117)May include surrounding context.

Run this as one command, with the code in place of CODE:

bash
d=~/.config/transcriptout; t=$(sed -n 's/.*"access_token":"\([^"]*\)".*/\1/p' "$d/signup.json"); (umask 077; curl -s -X POST https://api.transcriptout.com/auth/verify-cli -H "Authorization: Bearer $t" -H "Content-Type: application/json" -H "X-Client: youtube-skills-clawhub/youtube-playlist" -d '{"otp":"CODE","source":"youtube-skills-clawhub/youtube-playlist"}' -o "$d/verify.json"); k=$(sed -n 's/.*"api_key":"\([^"]*\)".*/\1/p' "$d/verify.json"); if [ -n "$k" ]; then (umask 077; printf '%s' "$k" > "$d/key"); rm -f "$d/signup.json"; echo stored; fi; grep -o '"code":"[^"]*"\|"credits":[0-9]*' "$d/verify.json"; rm -f "$d/verify.json"

It prints stored and the credit balance on success, or an error code. The key goes from the

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
85% confidence
Finding

Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

Content

Scanner excerpt · references/auth-setup.md (reported line 117)May include surrounding context.

Run this as one command, with the code in place of CODE:

bash
d=~/.config/transcriptout; t=$(sed -n 's/.*"access_token":"\([^"]*\)".*/\1/p' "$d/signup.json"); (umask 077; curl -s -X POST https://api.transcriptout.com/auth/verify-cli -H "Authorization: Bearer $t" -H "Content-Type: application/json" -H "X-Client: youtube-skills-clawhub/youtube-playlist" -d '{"otp":"CODE","source":"youtube-skills-clawhub/youtube-playlist"}' -o "$d/verify.json"); k=$(sed -n 's/.*"api_key":"\([^"]*\)".*/\1/p' "$d/verify.json"); if [ -n "$k" ]; then (umask 077; printf '%s' "$k" > "$d/key"); rm -f "$d/signup.json"; echo stored; fi; grep -o '"code":"[^"]*"\|"credits":[0-9]*' "$d/verify.json"; rm -f "$d/verify.json"

It prints stored and the credit balance on success, or an error code. The key goes from the

Chaining Abuse

High
Category
Tool Misuse
Confidence
75% confidence
Finding

Tool calls are chained to bypass individual safety checks or escalate capabilities beyond what any single tool call would allow.

Content

Scanner excerpt · references/auth-setup.md (reported line 117)May include surrounding context.

Run this as one command, with the code in place of CODE:

bash
d=~/.config/transcriptout; t=$(sed -n 's/.*"access_token":"\([^"]*\)".*/\1/p' "$d/signup.json"); (umask 077; curl -s -X POST https://api.transcriptout.com/auth/verify-cli -H "Authorization: Bearer $t" -H "Content-Type: application/json" -H "X-Client: youtube-skills-clawhub/youtube-playlist" -d '{"otp":"CODE","source":"youtube-skills-clawhub/youtube-playlist"}' -o "$d/verify.json"); k=$(sed -n 's/.*"api_key":"\([^"]*\)".*/\1/p' "$d/verify.json"); if [ -n "$k" ]; then (umask 077; printf '%s' "$k" > "$d/key"); rm -f "$d/signup.json"; echo stored; fi; grep -o '"code":"[^"]*"\|"credits":[0-9]*' "$d/verify.json"; rm -f "$d/verify.json"

It prints stored and the credit balance on success, or an error code. The key goes from the

Chaining Abuse

High
Category
Tool Misuse
Confidence
75% confidence
Finding

Tool calls are chained to bypass individual safety checks or escalate capabilities beyond what any single tool call would allow.

Content

Scanner excerpt · references/auth-setup.md (reported line 117)May include surrounding context.

Run this as one command, with the code in place of CODE:

bash
d=~/.config/transcriptout; t=$(sed -n 's/.*"access_token":"\([^"]*\)".*/\1/p' "$d/signup.json"); (umask 077; curl -s -X POST https://api.transcriptout.com/auth/verify-cli -H "Authorization: Bearer $t" -H "Content-Type: application/json" -H "X-Client: youtube-skills-clawhub/youtube-playlist" -d '{"otp":"CODE","source":"youtube-skills-clawhub/youtube-playlist"}' -o "$d/verify.json"); k=$(sed -n 's/.*"api_key":"\([^"]*\)".*/\1/p' "$d/verify.json"); if [ -n "$k" ]; then (umask 077; printf '%s' "$k" > "$d/key"); rm -f "$d/signup.json"; echo stored; fi; grep -o '"code":"[^"]*"\|"credits":[0-9]*' "$d/verify.json"; rm -f "$d/verify.json"

It prints stored and the credit balance on success, or an error code. The key goes from the

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 38)May include surrounding context.

md
## API Reference

Base URL: `https://api.transcriptout.com/v1`. Full reference with the latest parameters and schemas: [transcriptout.com/docs](https://transcriptout.com/docs?utm_source=youtube-skills&utm_medium=clawhub&utm_content=youtube-playlist).

## GET /v1/playlist/videos · 1 credit/page

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 46)May include surrounding context.

bash
# First page (100 videos)
curl -s "https://api.transcriptout.com/v1/playlist/videos?id=PL_ID_OR_URL" \
  -H "Authorization: Bearer $TRANSCRIPTOUT_API_KEY" \
  -H "X-Client: youtube-skills-clawhub/youtube-playlist"

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 51)May include surrounding context.

md
-H "X-Client: youtube-skills-clawhub/youtube-playlist"

# Next pages
curl -s "https://api.transcriptout.com/v1/playlist/videos?next_page_token=%2A%2A%2A" \
  -H "Authorization: Bearer $TRANSCRIPTOUT_API_KEY" \
  -H "X-Client: youtube-skills-clawhub/youtube-playlist"

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 56)May include surrounding context.

-H "X-Client: youtube-skills-clawhub/youtube-playlist"

IDs only, 500 per page (feed these into the bulk job)

curl -s "https://api.transcriptout.com/v1/playlist/videos?id=PL_ID_OR_URL&ids_only=true"
-H "Authorization: Bearer $TRANSCRIPTOUT_API_KEY"
-H "X-Client: youtube-skills-clawhub/youtube-playlist"

text

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 81)May include surrounding context.

bash
# 1. Collect the playlist's IDs
curl -s "https://api.transcriptout.com/v1/playlist/videos?id=PL_ID&ids_only=true" \
  -H "Authorization: Bearer $TRANSCRIPTOUT_API_KEY" \
  -H "X-Client: youtube-skills-clawhub/youtube-playlist"

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 93)May include surrounding context.

-d '{"videos":["ID1","ID2","..."],"format":"text"}'

3. Progress and results

curl -s "https://api.transcriptout.com/v1/transcripts/JOB_ID"
-H "Authorization: Bearer $TRANSCRIPTOUT_API_KEY"
-H "X-Client: youtube-skills-clawhub/youtube-playlist"

text

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 46)May include surrounding context.

bash
# First page (100 videos)
curl -s "https://api.transcriptout.com/v1/playlist/videos?id=PL_ID_OR_URL" \
  -H "Authorization: Bearer $TRANSCRIPTOUT_API_KEY" \
  -H "X-Client: youtube-skills-clawhub/youtube-playlist"

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 68)May include surrounding context.

Find videos inside a playlist by a substring of the title (case-insensitive). YouTube has no native playlist search, so this scans up to 500 playlist items.

bash
curl -s "https://api.transcriptout.com/v1/playlist/search?id=PL_ID_OR_URL&q=QUERY&limit=30" \
  -H "Authorization: Bearer $TRANSCRIPTOUT_API_KEY" \
  -H "X-Client: youtube-skills-clawhub/youtube-playlist"

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 86)May include surrounding context.

md
-H "X-Client: youtube-skills-clawhub/youtube-playlist"

# 2. One bulk job for every video
curl -s -X POST "https://api.transcriptout.com/v1/transcripts" \
  -H "Authorization: Bearer $TRANSCRIPTOUT_API_KEY" \
  -H "X-Client: youtube-skills-clawhub/youtube-playlist" \
  -H "Content-Type: application/json" \

Session Persistence

Medium
Category
Rogue Agent
Confidence
60% confidence
Finding

Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Content

Scanner excerpt · references/auth-setup.md (reported line 61)May include surrounding context.

it and writes the private file:

bash
mkdir -p ~/.config/transcriptout && chmod 700 ~/.config/transcriptout && (umask 077; printf 'TranscriptOut key: '; stty -echo; IFS= read -r k; stty echo; echo; printf '%s' "$k" > ~/.config/transcriptout/key)

Then continue with Load the key below.

Session Persistence

Medium
Category
Rogue Agent
Confidence
60% confidence
Finding

Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Content

Scanner excerpt · references/auth-setup.md (reported line 91)May include surrounding context.

Run this as one command, with the user's address in place of USER_EMAIL:

bash
mkdir -p ~/.config/transcriptout && chmod 700 ~/.config/transcriptout && (umask 077; curl -s -X POST https://api.transcriptout.com/auth/register-cli -H "Content-Type: application/json" -H "X-Client: youtube-skills-clawhub/youtube-playlist" -d '{"email":"USER_EMAIL","source":"youtube-skills-clawhub/youtube-playlist"}' -o ~/.config/transcriptout/signup.json); grep -o '"ok":[a-z]*\|"code":"[^"]*"' ~/.config/transcriptout/signup.json

It prints only "ok":true, or "ok":false with an error code. The response itself holds

The skill implements account registration and API-key issuance despite the manifest excluding account chores.

Medium
Category
Excessive Agency
Confidence
87% confidence
Finding

Path B instructs the agent to register a TranscriptOut account through /auth/register-cli and exchange an emailed verification code through /auth/verify-cli to issue and persist an API key. It explicitly supports signing into existing accounts and issuing new keys as well. These account-provisioning operations go beyond playlist retrieval and transcription and conflict with the manifest's instruction to skip account chores.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
93% confidence
Finding

Sending the supplied email address to the disclosed registration service is expected, not inherently exfiltration. However, the instruction to substitute the address directly into a single-quoted shell argument creates a command-injection hazard: an address containing a quote can break shell quoting, and malicious input can introduce commands before server-side validation occurs.

Content

Scanner excerpt · references/auth-setup.md (reported line 91)May include surrounding context.

Run this as one command, with the user's address in place of USER_EMAIL:

bash
mkdir -p ~/.config/transcriptout && chmod 700 ~/.config/transcriptout && (umask 077; curl -s -X POST https://api.transcriptout.com/auth/register-cli -H "Content-Type: application/json" -H "X-Client: youtube-skills-clawhub/youtube-playlist" -d '{"email":"USER_EMAIL","source":"youtube-skills-clawhub/youtube-playlist"}' -o ~/.config/transcriptout/signup.json); grep -o '"ok":[a-z]*\|"code":"[^"]*"' ~/.config/transcriptout/signup.json

It prints only "ok":true, or "ok":false with an error code. The response itself holds

External Transmission

Medium
Category
Data Exfiltration
Confidence
93% confidence
Finding

This duplicates the registration-command finding: the service URL is not itself evidence of malicious transmission. The actual vulnerability is the prescribed insertion of an untrusted email address into a single-quoted shell command, which can permit local command execution if followed literally.

Content

Scanner excerpt · references/auth-setup.md (reported line 91)May include surrounding context.

Run this as one command, with the user's address in place of USER_EMAIL:

bash
mkdir -p ~/.config/transcriptout && chmod 700 ~/.config/transcriptout && (umask 077; curl -s -X POST https://api.transcriptout.com/auth/register-cli -H "Content-Type: application/json" -H "X-Client: youtube-skills-clawhub/youtube-playlist" -d '{"email":"USER_EMAIL","source":"youtube-skills-clawhub/youtube-playlist"}' -o ~/.config/transcriptout/signup.json); grep -o '"ok":[a-z]*\|"code":"[^"]*"' ~/.config/transcriptout/signup.json

It prints only "ok":true, or "ok":false with an error code. The response itself holds

External Transmission

Medium
Category
Data Exfiltration
Confidence
85% confidence
Finding

Submitting the signup token and OTP to the same service is a legitimate authentication operation. The command nevertheless instructs direct substitution of the supplied code into shell source without enforced validation; if a response is substituted verbatim rather than restricted to six digits, shell metacharacters can escape the argument and execute commands.

Content

Scanner excerpt · references/auth-setup.md (reported line 117)May include surrounding context.

Run this as one command, with the code in place of CODE:

bash
d=~/.config/transcriptout; t=$(sed -n 's/.*"access_token":"\([^"]*\)".*/\1/p' "$d/signup.json"); (umask 077; curl -s -X POST https://api.transcriptout.com/auth/verify-cli -H "Authorization: Bearer $t" -H "Content-Type: application/json" -H "X-Client: youtube-skills-clawhub/youtube-playlist" -d '{"otp":"CODE","source":"youtube-skills-clawhub/youtube-playlist"}' -o "$d/verify.json"); k=$(sed -n 's/.*"api_key":"\([^"]*\)".*/\1/p' "$d/verify.json"); if [ -n "$k" ]; then (umask 077; printf '%s' "$k" > "$d/key"); rm -f "$d/signup.json"; echo stored; fi; grep -o '"code":"[^"]*"\|"credits":[0-9]*' "$d/verify.json"; rm -f "$d/verify.json"

It prints stored and the credit balance on success, or an error code. The key goes from the

External Transmission

Medium
Category
Data Exfiltration
Confidence
85% confidence
Finding

This duplicates the verification-command finding, rather than identifying a separate untrusted destination. The security issue is conditional on literal substitution of unvalidated OTP input into shell source, which could allow injected commands to run with the agent's permissions.

Content

Scanner excerpt · references/auth-setup.md (reported line 117)May include surrounding context.

Run this as one command, with the code in place of CODE:

bash
d=~/.config/transcriptout; t=$(sed -n 's/.*"access_token":"\([^"]*\)".*/\1/p' "$d/signup.json"); (umask 077; curl -s -X POST https://api.transcriptout.com/auth/verify-cli -H "Authorization: Bearer $t" -H "Content-Type: application/json" -H "X-Client: youtube-skills-clawhub/youtube-playlist" -d '{"otp":"CODE","source":"youtube-skills-clawhub/youtube-playlist"}' -o "$d/verify.json"); k=$(sed -n 's/.*"api_key":"\([^"]*\)".*/\1/p' "$d/verify.json"); if [ -n "$k" ]; then (umask 077; printf '%s' "$k" > "$d/key"); rm -f "$d/signup.json"; echo stored; fi; grep -o '"code":"[^"]*"\|"credits":[0-9]*' "$d/verify.json"; rm -f "$d/verify.json"

It prints stored and the credit balance on success, or an error code. The key goes from the

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · references/auth-setup.md (reported line 172)May include surrounding context.

prints the account id and the credits, never the key:

bash
curl -s https://api.transcriptout.com/auth/me \
  -H "Authorization: Bearer $TRANSCRIPTOUT_API_KEY" \
  -H "X-Client: youtube-skills-clawhub/youtube-playlist"