meeting-recap
Pass
Audited by Gen Agent Trust Hub on Jul 1, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill triggers the execution of a local Python script (scripts/validate_minutes.py) to verify the structure of generated meeting minutes. This script uses standard Python libraries to perform regex-based parsing and does not access network or sensitive local resources.
- [PROMPT_INJECTION]: The skill processes external, untrusted meeting data (transcripts, notes, and chat logs), creating an indirect prompt injection attack surface. (1) Ingestion points: Raw meeting materials provided by the user in Phase 1 (SKILL.md). (2) Boundary markers: Absent; the instructions do not require the use of delimiters to wrap or isolate user-provided text. (3) Capability inventory: The skill can write Markdown files and execute a local validation script. (4) Sanitization: No explicit sanitization or filtering of the input content is defined in the SOP.
Audit Metadata