gtm-leadership
Fail
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: CRITICALEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: Automated security scanners have reported a confirmed detection of malware in the file 'references/experts.md'. The skill also contains plain-text references to external domains, specifically 'keithrosen.com' and 'forgetthefunnel.com', which are flagged as blacklisted or malicious by reputation scanners.
- [INDIRECT_PROMPT_INJECTION]: The skill presents a significant attack surface for indirect prompt injection by processing untrusted user data—such as candidate details and performance metrics—into templates for high-stakes HR deliverables like performance improvement plans (PIPs) and termination scripts. The ingestion points lack boundary markers or sanitization logic to prevent malicious instructions from being executed by the agent. Furthermore, the skill's instructions for the agent to run a local validation script, 'scripts/check-output.py', increase the potential impact of such an attack.
Recommendations
- CRITICAL: 1 file(s) identified as malware by FileRep - DO NOT USE
- AI detected serious security threats
- Contains 8 malicious URL(s) - DO NOT USE
Audit Metadata