ruthless-refactorer

Pass

Audited by Gen Agent Trust Hub on Jul 9, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill includes behavioral instructions that encourage the agent to operate outside of its provided toolset and constraints.
  • Evidence: "God Mode: If a tool is missing, INVENT IT." (SKILL.md)
  • [PROMPT_INJECTION]: The skill processes untrusted external source code which could contain malicious instructions designed to influence the agent's refactoring logic or behavior.
  • Ingestion points: The Reconnaissance phase instructs the agent to "Read target files FULLY" (SKILL.md).
  • Boundary markers: Absent; the instructions do not specify delimiters or provide warnings to ignore instructions embedded within the code being processed.
  • Capability inventory: The skill possesses file modification capabilities used during the "Execution" phase (SKILL.md).
  • Sanitization: Absent; no sanitization, validation, or filtering of the ingested code content is performed before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 9, 2026, 01:21 AM
Security Audit — agent-trust-hub — ruthless-refactorer