dev-coding-frontend
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- [Indirect Prompt Injection] (LOW): The skill workflow involves processing untrusted external data (User Case specs and backend implementation notes) to drive high-capability browser automation tools.\n
- Ingestion points: UC spec (Step 1) and backend implementation notes (Step 2) in SKILL.md.\n
- Boundary markers: No specific delimiters or safety instructions are defined to separate the specification data from the agent's instructions.\n
- Capability inventory: Provides access to browser navigation, typing, clicking, and snapshotting via mcp__playwright__browser tools.\n
- Sanitization: No sanitization or validation of the input specifications is mentioned before they are used to guide browser interactions.\n- [Data Exposure] (SAFE): Example code includes common authentication patterns and API calls. All data used in examples (e.g., test@test.com, /api/auth/login) are standard documentation placeholders.\n- [External Downloads] (SAFE): The documentation references well-known, trusted libraries from standard package registries.
Audit Metadata