lint
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the Bash tool to execute standard Ruby development and security commands, including
bundle exec rubocop,bundle exec erblint,bin/brakeman, and Git commands. These operations are restricted to the local environment and align with the skill's purpose of code quality management. - [INDIRECT_PROMPT_INJECTION]: This skill has an inherent attack surface for indirect prompt injection as it processes untrusted data from the codebase.
- Ingestion points: Source code files (Ruby, ERB) and output from linting tools are read into the agent's context via the Read and Bash tools.
- Boundary markers: No explicit delimiters or instructions are used to separate ingested code content from the system prompt or agent instructions.
- Capability inventory: The skill uses the
Bashtool, enabling file system writes and command execution if instructions embedded in code were followed. - Sanitization: There is no evidence of sanitization or escaping for the file content or tool outputs processed during the workflow.
Audit Metadata