j5ik2o-custom-linter-creator

Pass

Audited by Gen Agent Trust Hub on Jul 15, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill defines a framework where linter diagnostics are specifically designed to be interpreted as prompts by an agent, creating a multi-step execution chain.
  • Ingestion points: The generated rules are intended to analyze project source code, which constitutes untrusted external data.
  • Boundary markers: The provided diagnostic template (Problem: ... Repair: ... Scope: ... Rationale: ...) lacks explicit delimiters or instructions for the downstream agent to ignore instructions embedded within the code being analyzed.
  • Capability inventory: The skill facilitates the creation of rules for language ecosystems like ESLint, pylint, and Go analysis tools, which are typically executed in privileged environments (CI/CD or local development) and their output is trusted by the next agent in the pipeline.
  • Sanitization: No guidance or requirements are provided to sanitize or escape code snippets before they are interpolated into the diagnostic repair prompt.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 15, 2026, 03:33 PM
Security Audit — agent-trust-hub — j5ik2o-custom-linter-creator