skills/openclaw/skills/de-ai-ify/Gen Agent Trust Hub

de-ai-ify

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: LOW
Full Analysis
  • [Indirect Prompt Injection] (LOW): The skill's primary function is to process and transform external text data provided by the user.
  • Ingestion points: The skill takes input text for rewriting in SKILL.md examples.
  • Boundary markers: Absent; the skill relies on the agent's internal reasoning to distinguish instructions from content.
  • Capability inventory: None. The skill has no code, no subprocess calls, no file-write operations, and no network access.
  • Sanitization: Not applicable for a prompt-only skill.
  • Risk Assessment: While it processes untrusted data, it lacks the side-effect capabilities required for an exploit.
  • [No Code] (INFO): This skill is composed entirely of markdown instructions and a metadata JSON file. No executable logic, binary files, or scripts were found.
  • [Prompt Injection] (SAFE): No attempts to override system prompts, bypass safety filters, or extract system instructions were detected. The language is purely instructional for the stated purpose.
Audit Metadata
Risk Level
LOW
Analyzed
Feb 17, 2026, 03:55 AM