spec-grill

Pass

Audited by Gen Agent Trust Hub on Jun 21, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The helper script scripts/extract-signals.js executes the git command using node:child_process.execFileSync to retrieve commit history from the target repository. This is a standard development operation and uses a safe method that avoids shell interpolation.\n- [PROMPT_INJECTION]: The skill ingests untrusted data from the repository being analyzed (e.g., documentation and commit messages) to seed its capability suggestions, creating a potential surface for indirect prompt injection.\n
  • Ingestion points: README.md, spec/charter.md, and git log data processed in scripts/extract-signals.js.\n
  • Boundary markers: The skill mandates the generation of a diagnostic "Grill Report" and requires explicit human confirmation before any modifications are written to the filesystem.\n
  • Capability inventory: Local file reads, git log command execution, and file writing to spec/capabilities.md.\n
  • Sanitization: Instructions require the agent to apply a "3-Axis Predicate Test" (Authority, Distributional, and Manipulability axes) to verify that proposed behaviors and constraints align with user intent and are resistant to agent manipulation.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 21, 2026, 11:21 AM
Security Audit — agent-trust-hub — spec-grill