validate-plugin

Pass

Audited by Gen Agent Trust Hub on Jul 21, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill automates plugin validation by executing local shell and Python scripts (./scripts/validate-all-plugins.sh and scripts/validate-skills-schema.py). These operations are performed using restricted bash tool calls.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted plugin metadata and documentation files, which represents an ingestion surface for potentially malicious instructions embedded in plugin data.
  • Ingestion points: Target plugin directories containing plugin.json and SKILL.md files.
  • Boundary markers: Not explicitly defined in the agent instructions for data reading operations.
  • Capability inventory: The skill has access to file system reading, restricted bash command execution (python3, jq), and pattern matching tools (grep, glob).
  • Sanitization: Relies on specialized validation scripts to parse and evaluate the integrity of the plugin content.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 21, 2026, 11:31 AM
Security Audit — agent-trust-hub — validate-plugin