constitution-compliance-review

Pass

Audited by Gen Agent Trust Hub on Mar 29, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns, obfuscation, or unauthorized operations were detected. The skill's behavior is consistent with its stated purpose of auditing and scoring markdown files.
  • [PROMPT_INJECTION]: The skill ingests untrusted data from local files via the Read tool. While this presents an indirect prompt injection surface, the risk is negligible as the skill lacks high-impact capabilities such as network access, file writing, or command execution. It only produces an analysis report as output.
  • Ingestion points: Files read using the Read tool as specified in SKILL.md via the user-provided file path argument.
  • Boundary markers: None explicitly defined to isolate ingested content from agent instructions.
  • Capability inventory: None. The skill does not use subprocesses, network tools, or file-writing tools.
  • Sanitization: No sanitization or filtering of input content is performed before analysis.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 29, 2026, 03:28 AM
Security Audit — agent-trust-hub — constitution-compliance-review