soia-dev-agent-md-advisor

Pass

Audited by Gen Agent Trust Hub on Jul 16, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The installation process involves downloading the skill from the developer's official repository.
  • [COMMAND_EXECUTION]: To verify the 'Timeliness' of configuration files, the skill uses 'ls' and 'grep' to check if referenced paths and CLI tools exist on the local system.
  • [PROMPT_INJECTION]: The skill processes external configuration documents, which creates an indirect prompt injection attack surface.
  • Ingestion points: The skill reads AGENTS.md, CLAUDE.md, GEMINI.md, and various files within the .claude/ configuration directory.
  • Boundary markers: It follows a strict diagnostic workflow where results are presented to the user before any changes are applied, and all file writes require explicit confirmation.
  • Capability inventory: The skill is capable of reading and writing specific configuration files and executing basic system utilities for verification.
  • Sanitization: The skill analyzes the content of files for design quality without implementing specific sanitization filters for the input text.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 16, 2026, 09:25 AM
Security Audit — agent-trust-hub — soia-dev-agent-md-advisor