recipe-reverse-engineer

Pass

Audited by Gen Agent Trust Hub on Mar 13, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious instructions, obfuscation, or unauthorized access patterns were identified. The skill follows best practices for orchestrating complex tasks through internal delegation.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests external codebase data for analysis, creating a theoretical surface for indirect prompt injection via code comments. However, this risk is inherent to the primary function of documentation generation and is mitigated by the skill's multi-agent verification loop and human review checkpoints.
  • Ingestion points: Codebase path provided via arguments or user questions.
  • Boundary markers: No specific delimiters or safety instructions are used when passing code content to sub-agents.
  • Capability inventory: Internal orchestration, task state management, and documentation file generation.
  • Sanitization: No explicit sanitization of codebase content before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 13, 2026, 11:03 AM