specforge-intake

Pass

Audited by Gen Agent Trust Hub on May 12, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes local Node.js scripts status.mjs and create-change.mjs located within the .specforge/tools/ directory to manage the project workflow.
  • [DATA_EXPOSURE]: The agent reads local project files including attention.md, registry.yaml, and project specifications from the .specforge/ directory to gather necessary context.
  • [PROMPT_INJECTION]: The skill processes untrusted user input to generate project documentation. 1. Ingestion points: user requests and original-request.md. 2. Boundary markers: uses .specforge/rules/boundaries.md for scope control. 3. Capability inventory: file system writes and local shell execution. 4. Sanitization: implements spec-quality.md rules to identify and mark ambiguity with [NEEDS CLARIFICATION].
Audit Metadata
Risk Level
SAFE
Analyzed
May 12, 2026, 10:43 AM
Security Audit — agent-trust-hub — specforge-intake