skills/poteto/noodle/refine/Gen Agent Trust Hub

refine

Pass

Audited by Gen Agent Trust Hub on Mar 22, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it processes untrusted data from an external file to perform its core functions.
  • Ingestion points: Content is ingested from brain/todos.md during the triage and rewrite steps.
  • Boundary markers: There are no delimiters or instructions to ignore instructions found within the todo items.
  • Capability inventory: The skill can modify the local file system via the Edit tool and interact with the user via AskUserQuestion.
  • Sanitization: Content read from the file is not sanitized or validated before being processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 22, 2026, 01:16 AM