using-superpowers
Pass
Audited by Gen Agent Trust Hub on May 7, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill employs extremely forceful and absolute language such as "EXTREMELY-IMPORTANT", "absolute must", and "non-negotiable" to force the agent into a specific tool-use loop. This is designed to override default behavioral constraints and prioritize the skill's workflow.
- [PROMPT_INJECTION]: The "Instruction Priority" section explicitly instructs the agent to override default system behavior ("Superpowers 技能覆盖默认系统提示行为"), which is a common pattern in prompt injection to bypass established safety or operational guidelines.
- [COMMAND_EXECUTION]: The file
references/codex-tools.mdcontains Bash script snippets intended for environment detection (e.g.,git rev-parse --git-dir). While used for identifying Git context, they represent executable shell logic embedded in the skill documentation.
Audit Metadata