plan-critiquer

Pass

Audited by Gen Agent Trust Hub on Mar 13, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns, command execution, or obfuscation were detected. The skill is composed of markdown instructions and templates.
  • [DATA_EXFILTRATION]: There are no indicators of data exfiltration. The skill does not perform network requests and does not access sensitive credential files.
  • [REMOTE_CODE_EXECUTION]: No remote code execution or package installation patterns were found.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection via the strategic documents it analyzes (Ingestion points: Strategic documents in SKILL.md; Boundary markers: absent; Capability inventory: Local file read and write operations; Sanitization: absent). However, the 'Skeptical Investor' persona and multi-pass framework provide a behavioral context that focuses on critical analysis, which significantly mitigates the risk of the agent following adversarial instructions embedded in documents.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 13, 2026, 06:57 PM