list-building

Fail

Audited by Gen Agent Trust Hub on Aug 17, 2026

Risk Level: CRITICALREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [REMOTE_CODE_EXECUTION]: Automated reputation scanners flagged the file SKILL.md as malicious (FileRepMalware). Additionally, instructions in SKILL.md and several sub-skills (e.g., define-icp/SKILL.md, qualify-accounts/SKILL.md) direct the user to execute npx -y @coldiq/mcp@latest. The -y flag bypasses confirmation, downloading and executing a remote package from the npm registry automatically. Although the package is associated with the vendor cold-iq, this pattern is a high-risk remote code execution vector.
  • [EXTERNAL_DOWNLOADS]: The resource file resources/list-building-advanced/list-building-directories.md includes a reference to saasmag.com, which is currently blacklisted by reputation scanners for malicious activity.
  • [INDIRECT_PROMPT_INJECTION]: The skill is architected to ingest and qualify prospect data from untrusted external sources like web scrapers, webhooks, and third-party databases. Ingestion points: External data enters the context in source-companies/SKILL.md and find-contacts/SKILL.md. Boundary markers: The skill lacks delimiters or instructions to ignore embedded commands in imported data. Capability inventory: The skill has access to file discovery tools (Glob) and network-active enrichment tools (mcp__coldiq__*). Sanitization: There is no evidence of input validation or escaping for external content before it is processed by the AI agent.
Recommendations
  • CRITICAL: 1 file(s) identified as malware by FileRep - DO NOT USE
  • AI detected serious security threats
  • Contains 1 malicious URL(s) - DO NOT USE
Audit Metadata
Risk Level
CRITICAL
Analyzed
Aug 17, 2026, 06:01 AM
Security Audit — agent-trust-hub — list-building