using-superpowers

Pass

Audited by Gen Agent Trust Hub on Nov 13, 2026

Risk Level: SAFEPROMPT_INJECTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill employs high-pressure, imperative language designed to override the agent's default operational logic. Phrases such as 'ABSOLUTELY MUST', 'not negotiable', 'not optional', and 'You cannot rationalize your way out of this' are used to force the agent to follow these instructions over its internal guidelines.
  • The 'Red Flags' section specifically instructs the agent to disregard its own reasoning process (e.g., 'I need more context first', 'This is just a simple question') and replace it with the skill's mandated behavior.
  • [INDIRECT_PROMPT_INJECTION]: The skill establishes a workflow that significantly increases the attack surface for indirect prompt injection.
  • Ingestion points: The agent is instructed to read content from .superpowers/skills/[skill-name]/SKILL.md whenever there is even a '1% chance' a skill might apply.
  • Boundary markers: The skill lacks any instructions for the agent to sanitize or treat these external skill files as untrusted; instead, it explicitly commands the agent to 'Follow skill exactly'.
  • Capability inventory: The skill enables and maps powerful tools such as manage_todo_list, runSubagent, and various file operation tools, which would be executed based on the content of these ingested files.
  • Sanitization: No sanitization or verification of the external skill content is performed before the agent adopts its instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 13, 2026, 02:28 AM