meeting-notes
Pass
Audited by Gen Agent Trust Hub on Oct 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user-provided meeting transcripts and summaries, which serves as a potential vector for indirect prompt injection attacks.
- Ingestion points: Meeting transcripts, recording summaries, and chat logs provided by the user (SKILL.md).
- Boundary markers: No specific delimiters or 'ignore previous instructions' warnings are used to isolate user-provided material.
- Capability inventory: The skill can interact with external note-taking tools or the vendor-owned 'Scratchpad connector' to save generated notes.
- Sanitization: The skill demonstrates security awareness by explicitly instructing the agent to omit door codes and passwords (Instruction 8) and to keep private data out of recaps (Instruction 9).
- [SAFE]: No malicious code, obfuscation, or unauthorized data exfiltration patterns were detected. The skill's functionality aligns with its stated purpose and includes best-practice data handling instructions.
Audit Metadata