meeting-report
Pass
Audited by Gen Agent Trust Hub on May 1, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface through the ingestion of external data files.
- Ingestion points: The skill reads .vtt transcripts and .csv attendance reports provided in the user prompt (documented in SKILL.md workflow steps 1 and 3).
- Boundary markers: Absent. There are no instructions to use delimiters or specific prompt engineering to isolate untrusted transcript content from the agent's core instructions.
- Capability inventory: The agent has access to Write for file system modification and Bash for system state discovery (e.g., git remote -v, ls).
- Sanitization: The instructions lack requirements for sanitizing or escaping the content extracted from the transcript files before incorporating them into the generated report.
Audit Metadata