meeting-minutes
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted data in the form of meeting notes or chat logs.
- Ingestion points: The workflow in
SKILL.mdinstructs the agent to collect "oral points / shorthand / chat records" provided by the user for summarization. - Boundary markers: There are no explicit delimiters or specific instructions provided to the agent to treat the ingested data solely as content rather than potential instructions.
- Capability inventory: The skill is limited to generating text output within the chat interface. It does not utilize tools for command execution, file system modification, or network requests.
- Sanitization: No input sanitization or validation mechanisms are implemented to filter malicious payloads in the meeting notes.
Audit Metadata