okr-capture

Pass

Audited by Gen Agent Trust Hub on May 14, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill facilitates the capture of untrusted user input into local markdown files, which is a surface for indirect prompt injection.
  • Ingestion points: User input provided as text or notes in SKILL.md (Phase 1).
  • Boundary markers: Present. The skill mandates a confirmation step in Phase 3 and wraps user content in blockquotes within the 'Context gốc' section of the output file.
  • Capability inventory: File creation (writing .md files to the .okr/inbox/ directory).
  • Sanitization: Absent. User input is stored as provided, though it is visually separated in the markdown structure.
Audit Metadata
Risk Level
SAFE
Analyzed
May 14, 2026, 02:38 AM
Security Audit — agent-trust-hub — okr-capture