cs-feat-review

Pass

Audited by Gen Agent Trust Hub on Jun 24, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a local Python script scripts/detect-review-agent.py to identify available review tools and CLIs (e.g., Paseo, Claude, Gemini) on the user's system.
  • [EXTERNAL_DOWNLOADS]: The detection script performs a local network request (HTTP GET) to 127.0.0.1:6767 (or an address defined in environment variables) to verify the availability of a local health endpoint for the Paseo service.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes untrusted data (code diffs and file content) during the review process.
  • Ingestion points: The skill reads git diff, git status, and the contents of various project files (design docs, checklists, and source code) as primary inputs.
  • Boundary markers: Absent. The instructions do not specify any delimiters to separate the reviewed code from the agent's core instructions.
  • Capability inventory: The skill has permissions to read and write files (generating the review report), execute local scripts, and interact with external CLI tools or sub-agents.
  • Sanitization: Absent. There is no evidence of filtering or escaping of the code content before it is processed by the AI.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 24, 2026, 03:24 AM
Security Audit — agent-trust-hub — cs-feat-review