pm-agent
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION] (SAFE): The instructions explicitly reinforce safety and operational constraints through a mandatory 'Constitution'. There are no attempts to bypass safety filters or ignore instructions.
- [DATA_EXFILTRATION] (SAFE): No unauthorized network activity or sensitive file access was found. The Telegram integration is a documented feature for human oversight.
- [REMOTE_CODE_EXECUTION] (SAFE): The skill does not download or execute code from external sources. The Python snippets provided are logic templates referencing internal modules.
- [CREDENTIALS_UNSAFE] (SAFE): No hardcoded secrets or API keys are present in the skill files.
Audit Metadata