eslint-plugin-custom-rule
Pass
Audited by Gen Agent Trust Hub on Nov 1, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to run a local script located at 'packages/eslint-plugin-cds/scripts/scaffold-new-rule.mjs' to generate the file structure for new ESLint rules. This is an expected development workflow within the project's repository.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied natural language descriptions and code examples to generate functional ESLint rules and test cases. While this involves processing untrusted data, it is the core intended functionality of the tool.
- Ingestion points: User descriptions of rule behavior and provided valid/invalid code examples (SKILL.md steps 2 and 3).
- Boundary markers: No explicit delimiters or boundary instructions are used to isolate user input.
- Capability inventory: Execution of local scripts and writing of new rule and test files.
- Sanitization: The skill relies on the agent's logic to interpret user input and does not specify explicit sanitization or validation of the provided examples.
Audit Metadata