pitstop
Pass
Audited by Gen Agent Trust Hub on Jul 21, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security issues detected. The skill consists entirely of instructional text without any executable scripts or external dependencies.
- [PROMPT_INJECTION]: Instructions to 'ignore preamble' or 'suppress tangents' are stylistic constraints for the requested 'pitstop' persona and do not constitute a bypass of safety filters or an attempt to extract system prompts. The skill explicitly reinforces safety protocols for destructive operations.
- [COMMAND_EXECUTION]: The skill does not execute any commands. While it references shell commands like
rm -rfin examples, it does so to instruct the agent to prioritize safety and user confirmation for such actions.
Audit Metadata