md-meeting-notes

Pass

Audited by Gen Agent Trust Hub on Feb 27, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface because it processes untrusted markdown transcripts provided by users or external sources.
  • Ingestion points: Untrusted data enters the agent context via the Read tool, which accesses files in the Meeting notes/ folder as described in SKILL.md.
  • Boundary markers: Absent. The skill instructions do not provide specific delimiters or warnings to the agent to disregard instructions that might be embedded within the transcripts.
  • Capability inventory: The skill utilizes Write, Read, Glob, Grep, and AskUserQuestion. It has the capability to write summaries to the local filesystem.
  • Sanitization: Absent. The skill does not perform escaping or filtering of the transcript content before it is processed by the language model.
  • Mitigation: The risk is partially mitigated by the requirement for user confirmation via AskUserQuestion at Step 1 (file selection) and Step 4 (summary review) before any files are written to disk.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 27, 2026, 06:07 PM