Skills
skills/clerk/cli/audit-clerk-skill/Gen Agent Trust Hub

audit-clerk-skill

Pass

Audited by Gen Agent Trust Hub on Apr 22, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes bun run format to maintain consistency in documentation style after applying updates, which is standard development behavior.
  • [PROMPT_INJECTION]: An indirect prompt injection surface exists as the skill processes source code from the repository to update documentation. This is a functional requirement of the skill. 1. Ingestion points: Reads code from packages/cli-core/src/commands/. 2. Boundary markers: None used for ingested code. 3. Capability inventory: File write access and shell command execution. 4. Sanitization: No sanitization is performed on the ingested source content.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 22, 2026, 03:42 PM