meeting-action-extractor
Pass
Audited by Gen Agent Trust Hub on Sep 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists entirely of instructional markdown to guide an LLM in extracting action items from text. It does not perform any file system operations, network requests, or command execution.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data in the form of meeting notes or transcripts, which is an inherent surface for indirect prompt injection. However, the risk is negligible as the skill lacks any capabilities to take action outside of text generation.
- Ingestion points: Meeting notes or transcripts provided as user input.
- Boundary markers: None specified in the instructions.
- Capability inventory: None; the skill is limited to generating markdown output.
- Sanitization: None; the skill summarizes input text as provided.
Audit Metadata