process-meeting-notes

Pass

Audited by Gen Agent Trust Hub on Jun 24, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill uses the official @anthropic/fireflies-mcp server and the standard GitHub CLI (gh) for its core operations. These are well-known and trusted external resources.
  • [SAFE]: The skill's workflows include mandatory user confirmation steps (e.g., in workflows/process-recent-meeting.md Step 6) before any action that modifies the user's environment or repository is taken.
  • [PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection as it processes untrusted meeting transcripts from an external API.
  • Ingestion points: workflows/process-recent-meeting.md (Steps 2 and 3) and workflows/create-issues-from-notes.md (Step 1) fetch transcript data.
  • Boundary markers: Content is interpolated into workflows without explicit boundary markers or instructions to ignore embedded commands.
  • Capability inventory: The skill has access to gh issue create (Command Execution) and Write (File System) tools.
  • Sanitization: No specific sanitization or filtering is applied to the transcript content; however, the risk is mitigated by the 'human-in-the-loop' confirmation requirement before any issue is created or file is written.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 24, 2026, 12:55 AM
Security Audit — agent-trust-hub — process-meeting-notes