ultra-clean

Pass

Audited by Gen Agent Trust Hub on Aug 20, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill represents a surface for indirect prompt injection because its core function involves ingesting and processing an entire repository's codebase.
  • Ingestion points: The agent maps and reads all source files within the repository during the baseline pass (documented in SKILL.md and references/baseline.md).
  • Boundary markers: The instructions do not define specific delimiters or instructions to treat data within the source files as potentially untrusted instructions, although they do emphasize preserving behavior.
  • Capability inventory: The skill has broad capabilities including file system writes across the repository and execution of shell-based validation tools (references/baseline.md, SKILL.md).
  • Sanitization: There is no explicit sanitization or filtering of the code content before it is processed by the cleaning lanes.
  • [SAFE]: All external tools referenced (knip, madge, tsc, eslint) are industry-standard developer tools. The skill explicitly recommends using repo-native tooling first and requires high-confidence evidence before any implementation, which aligns with security best practices for automated refactoring tools.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 20, 2026, 07:14 PM
Security Audit — agent-trust-hub — ultra-clean