doc-coauthoring

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [Trusted Source] (SAFE): The skill originates from the anthropics/skills repository, a verified trusted source.
  • [No Executable Code] (SAFE): The skill consists of a procedural workflow and metadata without any Python scripts, Node.js packages, or shell commands.
  • [Indirect Prompt Injection] (SAFE): The skill has a data ingestion surface but no exploitable capabilities. 1. Ingestion points: User-provided context and draft sections. 2. Boundary markers: Absent. 3. Capability inventory: No subprocess calls, network ops, or file writes across the skill. 4. Sanitization: Absent. The lack of capabilities renders this surface benign.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 05:29 PM