agent-sort

Pass

Audited by Gen Agent Trust Hub on Sep 12, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted local repository data to make configuration decisions.
  • Ingestion points: The workflow involves reading repository files (e.g., package.json, pyproject.toml) and file listings (rg --files) as defined in the Core Workflow.
  • Boundary markers: The instructions do not define specific delimiters or instructions to ignore embedded prompts within the analyzed repository data.
  • Capability inventory: The skill identifies components for DAILY or LIBRARY buckets, generates an install plan, can create a router skill file in the .claude/skills/ directory, and hands off to other tools like configure-ecc.
  • Sanitization: The skill does not perform sanitization of the data read from the repository files before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 12, 2026, 03:39 PM
Security Audit — agent-trust-hub — agent-sort