frontend-code-review
Pass
Audited by Gen Agent Trust Hub on Mar 19, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface because it is designed to read and process untrusted data from external source code files which may contain instructions targeting the agent.
- Ingestion points: The skill ingests content from .tsx, .ts, and .js files during both pending-change and file-targeted reviews as defined in SKILL.md.
- Boundary markers: There are no explicit delimiters or boundary markers specified in the instructions to help the agent distinguish between code-to-be-reviewed and potential embedded instructions.
- Capability inventory: Based on the provided files, the skill is limited to generating text-based review reports. It does not define any capabilities for file writing, network operations, or subprocess execution.
- Sanitization: No sanitization, validation, or filtering of the file content is performed before processing.
- [NO_CODE]: The skill consists entirely of markdown documentation and rule catalogs, with no executable code, scripts, or binary files included.
Audit Metadata