lint-rule-development
Pass
Audited by Gen Agent Trust Hub on May 13, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill instructions utilize standard development tools such as
just,cargo, andpnpmfor project-specific tasks like rule generation and snapshot testing. These commands are typical for the Biome repository's development environment. - [PROMPT_INJECTION]: The skill identifies a surface for indirect prompt injection as it instructs the agent to read and process external JavaScript and JSON files used for testing lint rules.
- Ingestion points: Test specification files located in
tests/specs/nursery/(e.g.,invalid.js,valid.js,options.json). - Boundary markers: There are no explicit instructions or markers provided to the agent to ignore or isolate potential prompt injection attempts embedded within the test code snippets.
- Capability inventory: The agent is authorized to execute shell commands via
just,cargo, andpnpmto run tests and generate code. - Sanitization: No sanitization or validation of the contents of the test files is mentioned before they are processed by the agent.
Audit Metadata