foundation-meeting-agenda
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from user-provided files and project memory, creating a potential surface for indirect prompt injection.
- Ingestion points: Step 2 in 'SKILL.md' (loading '@file' references) and the 'Project Memory Contract' section (reading '.claude/pm-skills.local.md').
- Boundary markers: The skill utilizes a structured markdown template ('TEMPLATE.md'), but lacks explicit instructions to ignore directives potentially embedded in the ingested content.
- Capability inventory: File writing (agenda generation). No network or system-level command execution was identified.
- Sanitization: No input validation or sanitization routines are specified for external content.
Audit Metadata