Back to skill

Security audit

redreplier-mean-marketer

Security checks for vulnerabilities and agentic risk

Overview

ClawScan marks this skill benign because it found no definite harmful behavior, but confidence is medium and part of the referenced script could not be fully inspected.

The verdict is benign, but the evidence is incomplete: only half of the components were fully scanned, and the script analysis was partial. Consider waiting for a complete review before installing if you need confidence about the script’s behavior.

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
  • Rogue AgentSelf-Modification, Session Persistence
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (13)

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 55)May include surrounding context.

md
./scripts/mean-marketer.js setup # prompts, input hidden

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

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

md
printf %s "$TOKEN" | ./scripts/mean-marketer.js setup # or pipe it

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 96)May include surrounding context.

md
./scripts/mean-marketer.js config # show current config

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 97)May include surrounding context.

md
./scripts/mean-marketer.js config --min-score 60 # only surface leads scoring >= 60 (50-100)

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 98)May include surrounding context.

md
./scripts/mean-marketer.js config --enabled false # pause the whole loop

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 99)May include surrounding context.

md
./scripts/mean-marketer.js config --profanity false # keep it savage but swear-free

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 100)May include surrounding context.

md
./scripts/mean-marketer.js config --website <websiteId> # only nag about one monitored site

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 132)May include surrounding context.

md
./scripts/mean-marketer.js notify

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 160)May include surrounding context.

md
*/5 * * * * cd /path/to/redreplier-mean-marketer && node scripts/mean-marketer.js notify

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 171)May include surrounding context.

md
To test without scheduling anything, just run it once: `./scripts/mean-marketer.js notify`

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 215)May include surrounding context.

md
./scripts/mean-marketer.js triage --id <opportunity_id> --status APPROVED # or REJECTED

Skill declares no tool scope ('permissions' or 'allowed-tools') but code capabilities were detected: env, network.

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

Session Persistence

Medium
Category
Rogue Agent
Confidence
85% 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 · SKILL.md (reported line 84)May include surrounding context.

md
The token never appears in a command-line argument. `setup` reads it from a hidden prompt
or from stdin, and refuses a `--key` flag outright. Keep it out of your crontab too: the
cron examples below rely on the stored config file rather than an inline variable, so the
secret stays in one `600` file instead of being copied into `crontab -l` output, process
listings and backups.

To rotate or revoke, delete `~/.config/redreplier/config.json` and generate a new token at