contract-writing

Pass

Audited by Gen Agent Trust Hub on Aug 18, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious code, obfuscation, or persistence mechanisms were detected. The skill's behavior is consistent with its stated purpose of improving task planning and code verification.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests user requests and project configuration files (like policies and failure patterns) to generate markdown contracts. While this is a surface for indirect prompt injection, it is the primary intended function of the skill and no exploitative patterns were identified.\n
  • Ingestion points: Reads user request text and project-specific files in the .harnessed/ directory.\n
  • Boundary markers: None explicitly defined for delimiting untrusted input.\n
  • Capability inventory: Generation of verification commands (e.g., npm test, curl, grep) to be written to a local markdown file.\n
  • Sanitization: No explicit sanitization or validation of input data is described.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 18, 2026, 01:13 AM
Security Audit — agent-trust-hub — contract-writing