skill-linter

Pass

Audited by Gen Agent Trust Hub on Nov 16, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructions direct the agent to execute a local Python script (python scripts/validate.py) to perform mechanical validation of repository files. This is standard behavior for development and linting tools within a code hub environment.
  • [INDIRECT_PROMPT_INJECTION]: As a linter, the skill is designed to ingest and analyze untrusted external markdown files (SKILL.md). This creates a surface for indirect prompt injection if the analyzed content contains malicious instructions. The skill explicitly mitigates this risk by instructing the agent to identify and flag content that resembles malicious intent, such as data exfiltration or credential harvesting.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 16, 2026, 05:44 PM