review-ui
Pass
Audited by Gen Agent Trust Hub on Aug 19, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The agent is instructed to locate and execute the local development command defined in the project documentation (e.g., docs/agents/project.md) to start the application. This is a functional requirement for the skill to perform visual testing.
- [EXTERNAL_DOWNLOADS]: The skill uses npx playwright to capture screenshots. This involves the execution of a well-known, trusted browser automation tool and may involve downloading necessary binaries from official registries.
- [PROMPT_INJECTION]: The skill has an indirect prompt injection surface as it ingests content from repository files and documentation to guide its execution. 1. Ingestion points: local files identified by git diff and documentation in the docs/ folder. 2. Boundary markers: No explicit delimiters or ignore-instructions are used for external data. 3. Capability inventory: The skill has the ability to execute shell commands and drive a browser. 4. Sanitization: No sanitization is performed on ingested content before it is processed.
Audit Metadata