unknown

Pass

Audited by Gen Agent Trust Hub on Feb 21, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [No Code] (SAFE): This skill consists entirely of Markdown instructions and templates. No Python, Node.js, or shell scripts are present, significantly reducing the attack surface.
  • [Data Exposure & Exfiltration] (SAFE): The skill instructions mention scanning project context (README, plans, prior notes). While this involves reading local data, there are no network tools (curl, wget) or exfiltration patterns detected.
  • [Indirect Prompt Injection] (LOW): The skill is designed to ingest and analyze user-provided documents and project files.
  • Ingestion points: User strategy documents and local project context files.
  • Boundary markers: None specified.
  • Capability inventory: No executable tools, network access, or file-write capabilities.
  • Sanitization: Not present.
  • Risk Assessment: Although a malicious document could attempt to influence the agent's behavior, the skill's lack of dangerous tools (no internet or shell access) prevents significant exploitation.
  • [Prompt Injection] (SAFE): No attempts to override system safety guidelines or bypass AI constraints were found in the instructional text.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 21, 2026, 01:26 PM