meeting
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted input in the form of meeting transcripts and notes, which represents a potential surface for indirect prompt injection attacks.
- Ingestion points: The skill accepts user-provided transcripts, rough notes, and voice memo text in
SKILL.mdto generate summaries. - Boundary markers: There are no explicit boundary markers or instructions defined to prevent the agent from following commands that might be embedded within the provided notes.
- Capability inventory: The skill is limited to text summarization and formatting; it does not have access to tools, network operations, or file system modifications.
- Sanitization: No sanitization or input validation logic is present to filter malicious instructions from the source material.
Audit Metadata