craft-survey

Pass

Audited by Gen Agent Trust Hub on Apr 18, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: No malicious command execution, exfiltration, or obfuscated content was found.
  • [PROMPT_INJECTION]: The skill analyzes external references, creating an indirect prompt injection surface. 1. Ingestion points: Local and public references (SKILL.md). 2. Boundary markers: Absent. 3. Capability inventory: Recommending codebase edits. 4. Sanitization: Absent, but synthesis and citation requirements serve as mitigations by preventing verbatim instruction following.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 18, 2026, 01:22 AM