using-superpowers
Warn
Audited by Gen Agent Trust Hub on Feb 28, 2026
Risk Level: MEDIUMPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill utilizes strong behavioral override markers to force tool execution and bypass the agent's internal logic.
- Evidence: The skill uses imperative and absolute language such as "ABSOLUTELY MUST," "not negotiable," "not optional," and "You cannot rationalize your way out of this."
- Evidence: The "Red Flags" section explicitly instructs the agent to ignore its own reasoning and internal checks, labeling natural agent processes like "I need more context first" as rationalizations that must be stopped.
- [PROMPT_INJECTION]: The instructions mandate a dangerously low threshold for invoking external content.
- Evidence: The skill requires invocation if there is even a "1% chance" a skill might apply, which effectively overrides the agent's ability to selectively and safely choose tools, significantly increasing the attack surface for indirect prompt injection from other skill files.
Audit Metadata