aios-workflow-router

Pass

Audited by Gen Agent Trust Hub on May 8, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill has an indirect prompt injection surface because it processes untrusted user requests to determine task routing and generate documentation without using boundary markers or sanitization.
  • Ingestion points: User task descriptions are processed by the router in SKILL.md.
  • Boundary markers: Absent; user input is not wrapped in delimiters or accompanied by instructions to ignore embedded commands.
  • Capability inventory: The skill can write files to docs/plans/ and invoke powerful external tools via the superpowers:* namespace.
  • Sanitization: Absent; there is no evidence of validation or escaping for user-supplied strings before they are utilized in planning or workflow selection.
Audit Metadata
Risk Level
SAFE
Analyzed
May 8, 2026, 02:41 PM