clean-css

Pass

Audited by Gen Agent Trust Hub on May 15, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute the command git diff <base> --name-only to identify files modified in a branch. This is a standard developer operation for code review tasks.\n- [PROMPT_INJECTION]: The skill processes untrusted content from source code files, which presents a surface for indirect prompt injection.\n
  • Ingestion points: Reads and reviews various code files including .css, .module.css, .tsx, and .jsx.\n
  • Boundary markers: No explicit markers or instructions are provided to the agent to distinguish between its own rules and instructions that might be embedded in the code comments of the analyzed files.\n
  • Capability inventory: Uses the git command-line utility via the agent's shell access.\n
  • Sanitization: There is no mention of sanitizing file content or validating branch name arguments before they are used in the command.
Audit Metadata
Risk Level
SAFE
Analyzed
May 15, 2026, 04:56 PM
Security Audit — agent-trust-hub — clean-css