using-superpowers

Pass

Audited by Gen Agent Trust Hub on Mar 21, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: Ingestion points: The skill references the directory ~/.openclaw/extensions/superpowers/skills/ as a source for instruction files (SKILL.md). Boundary markers: No specific delimiters or safety warnings are provided for content ingested from these files. Capability inventory: The agent is instructed to 'Follow instructions exactly' and that 'Skills override default behavior' (SKILL.md). Sanitization: No sanitization or validation of the content within the skill files is described. This ingestion surface is associated with the primary intended purpose of the skill.
  • [PROMPT_INJECTION]: The skill uses directives like 'Follow instructions exactly' and 'Skills override default behavior' to establish the priority of functional extensions over default agent behavior.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 21, 2026, 05:55 AM