kernel-write-extract-posts
Pass
Audited by Gen Agent Trust Hub on Jul 13, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, base64 encoding, or suspicious network activity were found in the skill definitions or instructions.
- [PROMPT_INJECTION]: The skill processes user-provided essay content, which represents a surface for indirect prompt injection. Mandatory Evidence Chain: 1. Ingestion point: Path to polished essay file (SKILL.md). 2. Boundary markers: Absent. 3. Capability inventory: Read and Write tools (SKILL.md). 4. Sanitization: Absent, though output is constrained to valid JSON.
Audit Metadata