meeting-analysis
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze meeting transcripts, which are untrusted external data sources. This constitutes an indirect prompt injection surface. However, the skill lacks tool usage, network operations, or shell execution, limiting the potential impact. 1. Ingestion points: Meeting transcripts from Zoom, Google Meet, Fireflies.ai, and Otter.ai (as referenced in SKILL.md). 2. Boundary markers: Not specified in the skill logic. 3. Capability inventory: None; no code or tool execution capabilities were identified in the skill. 4. Sanitization: No specific sanitization or filtering logic is defined for the ingested transcripts.
- [SAFE]: The skill consists entirely of natural language instructions for behavioral analysis and lacks any executable scripts, remote dependencies, or configuration for privileged tools.
Audit Metadata