feature-dev

Pass

Audited by Gen Agent Trust Hub on Aug 8, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes local shell commands for version control (git) and project-specific test runners such as 'bin/rails test' or 'bundle exec rspec' to verify implementation.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its reliance on codebase content to guide the development process. 1. Ingestion points: Local codebase files analyzed during the Phase 2 exploration stage. 2. Boundary markers: Absent; there are no instructions to the agent to treat file content as untrusted data or to ignore embedded instructions. 3. Capability inventory: Significant, including shell command execution and file modification via TDD and code review fixes. 4. Sanitization: Absent; the skill does not specify any filtering or escaping of content read from the codebase before it is used to influence agent logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 8, 2026, 05:05 PM
Security Audit — agent-trust-hub — feature-dev