foundation-meeting-synthesize
Pass
Audited by Gen Agent Trust Hub on Oct 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection through its ingestion of untrusted meeting notes.
- Ingestion points: Reads meeting recap and raw note files (SKILL.md, line 62).
- Boundary markers: Lacks specific delimiters or instructions to the agent to ignore embedded instructions in the source content.
- Capability inventory: Capable of reading local files and writing to a persistent project memory file (.claude/pm-skills.local.md) as specified in the Project Memory Contract (SKILL.md, line 116).
- Sanitization: No sanitization, escaping, or validation of the input data is performed during the synthesis process.
Audit Metadata