meeting-minutes-ai
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted meeting transcripts provided by users, which could contain malicious instructions designed to subvert the agent's summarization or task extraction logic.
- Ingestion points: Meeting transcripts are ingested through the
extract_minutes.pyscript and the AI agent instructions inSKILL.md. - Boundary markers: The skill does not implement or require the use of explicit delimiters (e.g., XML tags or unique markers) to isolate untrusted transcript data from the system prompt.
- Capability inventory: The skill has the capability to read from and write to the local file system (e.g., generating
.mdfiles in the current working directory). - Sanitization: The extraction logic relies on basic regular expressions and LLM interpretation without specific sanitization of the input text to prevent instruction override.
Audit Metadata