plugin-audit

Pass

Audited by Gen Agent Trust Hub on Aug 15, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is composed strictly of informational markdown files, including best practices, changelogs, and checklists. It contains no executable code or scripts that could perform unauthorized actions.- [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze third-party plugin code and configuration files, creating a data ingestion surface. However, the risk is negligible as the skill lacks executable scripts or dangerous command patterns.
  • Ingestion points: The agent reads plugin files (plugin.json, markdown documentation) using Read, Glob, and Grep tools.
  • Boundary markers: Not explicitly defined in the reference materials.
  • Capability inventory: The skill contains no executable scripts or subprocess calls; it relies entirely on the agent's default tools for structural analysis.
  • Sanitization: No specific sanitization or filtering logic is provided for the audited content.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 15, 2026, 08:44 AM
Security Audit — agent-trust-hub — plugin-audit