expansion-playbook
Pass
Audited by Gen Agent Trust Hub on Feb 19, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [NO_CODE] (SAFE): The analyzed files contain only markdown instructions and configuration templates. No executable scripts (Python, JavaScript, etc.) are present.
- [DATA_EXPOSURE & EXFILTRATION] (SAFE): The skill describes workflows involving a connected knowledge base for business data. No mechanisms for data exfiltration or unauthorized file access were found.
- [PROMPT_INJECTION] (SAFE): No instructions attempting to override system prompts or bypass safety filters were detected.
- [INDIRECT PROMPT INJECTION] (SAFE): While the skill defines an ingestion point for external data (via the
~~knowledge baseplaceholder), it lacks any dangerous capabilities (such as command execution or network calls) that would make such an injection exploitable.
Audit Metadata