meeting-analyzer
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- Indirect Prompt Injection Surface: The skill is designed to ingest and process untrusted data from external sources, such as meeting transcripts, notes, and audio/video recordings. This introduces a potential surface for indirect prompt injection, where malicious instructions embedded in the meeting content could attempt to influence the agent's output or behavior.\n
- Ingestion points: Meeting content is ingested from text, notes, or audio/video recordings as described in
SKILL.mdandREADME.md.\n - Boundary markers: There are no specific delimiters or instructions to the agent to treat input as untrusted data or to disregard potential commands found within the meeting content.\n
- Capability inventory: The skill is limited to text generation for report delivery and does not have access to sensitive capabilities such as network requests, file-system writes, or code execution.\n
- Sanitization: The skill does not implement specific sanitization or filtering of the input content before processing it for analysis.
Audit Metadata