breaking-refactor

Pass

Audited by Gen Agent Trust Hub on Aug 4, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection due to its core function of processing untrusted repository data while possessing high-privilege capabilities.\n
  • Ingestion points: The agent is instructed to read the repository's working tree, code definitions, imports, schemas, fixtures, and documentation (SKILL.md, Workflow Step 1).\n
  • Boundary markers: There are no instructions to use delimiters or ignore embedded natural language instructions found within repository files.\n
  • Capability inventory: The workflow involves modifying source code, deleting files, and executing arbitrary repository build and test commands (SKILL.md, Workflow Steps 3 and 4).\n
  • Sanitization: No sanitization or filtering of external content is performed before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 4, 2026, 09:15 AM
Security Audit — agent-trust-hub — breaking-refactor