meeting-prep-briefer
Pass
Audited by Gen Agent Trust Hub on May 15, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: No security issues detected. The skill's behavior is consistent with its stated purpose of generating meeting briefs from local files.
- [PROMPT_INJECTION]: Evaluated the surface for indirect prompt injection from local files. Ingestion points: Workspace files (.md, .txt) in root and subdirectories (notes/, context/, etc.). Boundary markers: Absent; instructions do not specify delimiters for external content. Capability inventory: Local file read and write operations; no network tools (curl, wget) or shell execution capabilities are present. Sanitization: Absent; the skill extracts and displays note content directly. Conclusion: The surface exists but the risk is negligible as the agent has no access to tools that could be abused for exfiltration or persistence.
Audit Metadata