clean-up-comments

Pass

Audited by Gen Agent Trust Hub on Aug 11, 2026

Risk Level: SAFECREDENTIALS_UNSAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill utilizes documentation and resources from frontendchecklist.io, a well-known community standard for web development best practices.
  • [CREDENTIALS_UNSAFE]: The reference file references/rule.md contains examples of sensitive information, such as sk-1234567890abcdef and database connection strings. These are explicitly provided as negative examples to be removed from production code and do not constitute actual hardcoded secrets.
  • [COMMAND_EXECUTION]: Example cleanup scripts in references/rule.md include shell commands for file deletion (e.g., rm -rf .storybook/). These are educational templates intended for user-controlled automation environments rather than direct agent execution.
  • [PROMPT_INJECTION]: The skill operates on external templates and HTML files, creating an indirect prompt injection surface. The instructions mitigate this risk by scoping the agent's tasks strictly to the removal of specific markup patterns.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 11, 2026, 12:29 AM
Security Audit — agent-trust-hub — clean-up-comments