skills/zernie/vigiles/pr-to-lint-rule/Gen Agent Trust Hub

pr-to-lint-rule

Pass

Audited by Gen Agent Trust Hub on Apr 2, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection by processing untrusted natural language descriptions via the $ARGUMENTS parameter to generate code and documentation.
  • Ingestion points: The skill accepts user-supplied text for the PR feedback description in SKILL.md.
  • Boundary markers: There are no explicit delimiters or instructions to the model to ignore potential commands embedded within the user input.
  • Capability inventory: The skill provides the agent with the ability to create new source files (e.g., eslint-rules/, clippy.toml) and append content to CLAUDE.md.
  • Sanitization: No input validation is performed on the provided description before it is used to generate file content.
  • Risk mitigation: The skill explicitly instructs the agent to present all generated content to the user and request permission before writing any files, maintaining a human-in-the-loop requirement that mitigates the risk of unauthorized file modifications.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 2, 2026, 11:57 PM
Security Audit — agent-trust-hub — pr-to-lint-rule