review-doc-style

Pass

Audited by Gen Agent Trust Hub on Aug 1, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns, external dependencies, or security vulnerabilities were identified. The skill is composed entirely of technical writing guidelines and markdown-based reference documents.\n- [PROMPT_INJECTION]: The skill involves processing external documentation which represents a surface for indirect prompt injection. However, the risk is assessed as safe because the skill lacks functional capabilities for code execution, network requests, or sensitive file access.\n
  • Ingestion points: Reviews changed documentation and public-facing strings as described in SKILL.md.\n
  • Boundary markers: No specific delimiters are defined to separate user data from instructions.\n
  • Capability inventory: The skill is restricted to text review and providing recommendations; no tools for command execution or data modification are used.\n
  • Sanitization: No sanitization steps for the input documentation are mentioned.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 1, 2026, 12:36 AM
Security Audit — agent-trust-hub — review-doc-style