draft
Pass
Audited by Gen Agent Trust Hub on Jun 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns or security risks were identified during the analysis.
- [PROMPT_INJECTION]: The skill uses standard prompt interpolation to receive user instructions. It does not contain instructions to override safety filters or disregard previous rules.
- [DATA_EXPOSURE]: No hardcoded credentials, API keys, or sensitive file paths were found in the skill metadata or body.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user data via the
{{args}}variable and passes it to sub-skills. It uses backticks as boundary markers to differentiate user input from system instructions, which is a standard practice for dispatcher-style skills.
Audit Metadata