apply-code-conventions

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to detect and run project linters such as RuboCop or StandardRB based on existing configuration files like .rubocop.yml or .standard.yml.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes Rails source code and specifications from the local environment, which represents a potential attack surface if those files contain malicious instructions.
  • Ingestion points: The agent reads project files matching paths such as app/**/*.rb and spec/**/*_spec.rb as defined in the 'Apply by area' table.
  • Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded prompts within the source code being analyzed.
  • Capability inventory: The agent has the capability to execute shell commands for linting and perform file system writes to refactor code.
  • Sanitization: No explicit sanitization or validation steps are defined for handling instructions potentially embedded within the source code files.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 05:23 PM
Security Audit — agent-trust-hub — apply-code-conventions