collab-pm-report
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external sources including Notion, Linear, Asana, and user-provided text, creating a potential surface for indirect prompt injection.\n
- Ingestion points: Data is fetched via Notion, Linear, and Asana MCP tools, or from user-provided text as described in the workflow section of
SKILL.md.\n - Boundary markers: The skill does not define specific delimiters to separate external data from system instructions within its report templates.\n
- Capability inventory: The skill generates markdown text for reports and presentation slides but does not directly execute system commands, spawn subprocesses, or perform network operations.\n
- Sanitization: The skill recommends using
moai-lawyer:legal-nda-triageandmoai-coworker:ai-slop-reviewerto audit the generated content for sensitive data and quality issues, which acts as a mitigation strategy.
Audit Metadata