skills/bcgen/skills/retro/Gen Agent Trust Hub

retro

Pass

Audited by Gen Agent Trust Hub on Jul 8, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted conversation history to generate rules, documentation, and memory entries, creating a surface for indirect prompt injection.
  • Ingestion points: Current conversation history (SKILL.md, Step 1).
  • Boundary markers: No explicit delimiters or instructions are provided to the agent to ignore potentially malicious content within the history.
  • Capability inventory: The skill has the ability to write files to the .ai/ directory, project documentation, configuration files, and update agent memory (SKILL.md, Steps 3 & 4).
  • Sanitization: The skill includes a mandatory user consent step (Step 4) for every proposal, providing a human-in-the-loop safety check.
  • [COMMAND_EXECUTION]: The skill executes local development tools to analyze the project's effective configuration state.
  • Evidence: The routing logic mentions running commands such as eslint --print-config <file> to probe effective settings (references/routing.md).
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 8, 2026, 02:30 AM
Security Audit — agent-trust-hub — retro