plugin-validator

Pass

Audited by Gen Agent Trust Hub on Nov 7, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONPERSISTENCE
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes external tools including shellcheck and jq to audit plugin files. These calls are performed using safe subprocess execution with argument lists rather than shell strings, preventing command injection.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted plugin content (shell and Python scripts) for auditing. While this creates an ingestion surface for indirect prompt injection, the skill's capabilities are focused on pattern matching and reporting findings, with no automated execution of the content being analyzed.
  • [PERSISTENCE]: The SKILL.md file contains instructions for a 'Self-Evolving Skill' pattern, directing the agent to modify its own documentation to fix issues or improve practices. This is a documented maintenance mechanism for the agent and does not utilize traditional persistence vectors like shell profiles or crontabs.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 7, 2026, 02:12 AM