using-superpowers
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEPROMPT_INJECTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill employs extremely forceful and imperative language designed to override the agent's standard operational guidelines and user-provided instructions. It uses phrases such as "ABSOLUTELY MUST," "not negotiable," "not optional," and "automatic failure" to mandate specific workflows regardless of the direct user commands or task simplicity.
- [INDIRECT_PROMPT_INJECTION]: The skill establishes a mandatory process for the agent to find and execute external skills based on the current task context, which creates a vulnerability surface for indirect prompt injection.
- Ingestion points: The agent is instructed to evaluate the user's task and available file context to identify and run matching skills (SKILL.md).
- Boundary markers: The instructions lack any requirement to sanitize or validate the content of the skills being identified and executed.
- Capability inventory: The skill mandates the use of the
Skilltool to read and run arbitrary skill files and theTodoWritetool for task management. - Sanitization: No sanitization or verification mechanisms are described for the external skills being dynamically invoked.
Audit Metadata