Back to skill

Security audit

YouTube Search

Security checks for vulnerabilities and agentic risk

Overview

The skill provides YouTube research through a disclosed external service, with optional account setup and credential storage that fit its purpose.

TranscriptOut receives your searches and chosen video identifiers, and requests spend service credits. Prefer your runtime's secret prompt. Optional account setup shares your email and requires an emailed code; browser setup is also available. The fallback stores a local credential and changes your shell profile, so remove those settings and revoke the key when finished. Both bundled files were reviewed and the scanner's reference gaps were resolved; the provider's live behavior was not tested.

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 (21)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
97% confidence
Finding

The supplied chunk performs third-party registration rather than YouTube discovery. Although authentication can support a search service, this code initiates registration, an account-related action explicitly excluded by the description. The email value is a literal placeholder, so the chunk does not establish disclosure of a real user's email. Restrictive file permissions are appropriate but do not resolve the purpose mismatch.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
93% confidence
Finding

The supplied chunk implements an authentication setup workflow, not a YouTube search operation. Although authentication can support a search service, this chunk's entire purpose is account verification and API-key storage—account chores explicitly excluded by the description. It contains no video, channel, or creator discovery behavior.

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 $t" -H "Content-Type: application/json" -H "X-Client: youtube-skills-clawhub/youtube-search" -d '{"otp":"CODE","source":"youtube-skills-clawhub/youtube-search"}' -o "$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 $t" -H "Content-Type: application/json" -H "X-Client: youtube-skills-clawhub/youtube-search" -d '{"otp":"CODE","source":"youtube-skills-clawhub/youtube-search"}' -o "$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 $t" -H "Content-Type: application/json" -H "X-Client: youtube-skills-clawhub/youtube-search" -d '{"otp":"CODE","source":"youtube-skills-clawhub/youtube-search"}' -o "$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 $t" -H "Content-Type: application/json" -H "X-Client: youtube-skills-clawhub/youtube-search" -d '{"otp":"CODE","source":"youtube-skills-clawhub/youtube-search"}' -o "$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-search).

## GET /v1/search · 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
# Videos
curl -s "https://api.transcriptout.com/v1/search?q=QUERY&type=video&limit=20" \
  -H "Authorization: Bearer $TRANSCRIPTOUT_API_KEY" \
  -H "X-Client: youtube-skills-clawhub/youtube-search"

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-search"

# Channels
curl -s "https://api.transcriptout.com/v1/search?q=QUERY&type=channel&limit=10" \
  -H "Authorization: Bearer $TRANSCRIPTOUT_API_KEY" \
  -H "X-Client: youtube-skills-clawhub/youtube-search"

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-search"

Next page

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

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 75)May include surrounding context.

Search inside one channel using YouTube's native relevance search. A result whose title lacks the query word is normal: it is relevance, not substring match.

bash
curl -s "https://api.transcriptout.com/v1/channel/search?name=%40kurzgesagt&q=QUERY&limit=30" \
  -H "Authorization: Bearer $TRANSCRIPTOUT_API_KEY" \
  -H "X-Client: youtube-skills-clawhub/youtube-search"

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 95)May include surrounding context.

bash
# 1. Search
curl -s "https://api.transcriptout.com/v1/search?q=QUERY&limit=5" \
  -H "Authorization: Bearer $TRANSCRIPTOUT_API_KEY" \
  -H "X-Client: youtube-skills-clawhub/youtube-search"

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 100)May include surrounding context.

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

2. Transcript of a chosen result

curl -s "https://api.transcriptout.com/v1/transcript?video=VIDEO_ID&format=text&video_metadata=true"
-H "Authorization: Bearer $TRANSCRIPTOUT_API_KEY"
-H "X-Client: youtube-skills-clawhub/youtube-search"

text

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-search" -d '{"email":"USER_EMAIL","source":"youtube-skills-clawhub/youtube-search"}' -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 explicitly excluding account chores.

Medium
Category
Excessive Agency
Confidence
97% confidence
Finding

The manifest describes finding YouTube videos and channels and explicitly says to skip account chores. This workflow instead submits the user's email to register a TranscriptOut account (L091), verifies an emailed code and stores a newly issued API key (L117), and supports signing into existing accounts to issue additional keys (L133). These are account-management operations, not simply using an existing credential to perform searches.

Content

No source excerpt is available for this finding.

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 · 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-search" -d '{"email":"USER_EMAIL","source":"youtube-skills-clawhub/youtube-search"}' -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
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 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-search" -d '{"email":"USER_EMAIL","source":"youtube-skills-clawhub/youtube-search"}' -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
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 · 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 $t" -H "Content-Type: application/json" -H "X-Client: youtube-skills-clawhub/youtube-search" -d '{"otp":"CODE","source":"youtube-skills-clawhub/youtube-search"}' -o "$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 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 $t" -H "Content-Type: application/json" -H "X-Client: youtube-skills-clawhub/youtube-search" -d '{"otp":"CODE","source":"youtube-skills-clawhub/youtube-search"}' -o "$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-search"