write-skill

Pass

Audited by Gen Agent Trust Hub on May 12, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill is a documentation and scaffolding tool that does not contain malicious logic or scripts.
  • [COMMAND_EXECUTION]: Uses the ls command to check for existing skills to avoid naming collisions, which is a benign read-only operation.
  • [PROMPT_INJECTION]: The skill processes user input to populate templates for new skills, creating an indirect injection surface. Ingestion points: Step 1 (Clarify the skill) in SKILL.md; Boundary markers: Absent; Capability inventory: File system writes to the skills/ directory and README.md, and directory listing via ls; Sanitization: Absent.
Audit Metadata
Risk Level
SAFE
Analyzed
May 12, 2026, 07:53 PM
Security Audit — agent-trust-hub — write-skill