tdd
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted inputs from web content and external data sources via BrowserOS, which introduces a potential surface for indirect prompt injection attacks.
- Ingestion points: External data and web content accessed via BrowserOS as specified in SKILL.md.
- Boundary markers: Instructions in SKILL.md explicitly state that web content and external data must be treated as hostile.
- Capability inventory: The skill is capable of executing terminal actions via the ExecutionProxy Interface and managing files via MemoryStore as described in SKILL.md.
- Sanitization: The protocol requires redacting secrets and PII before sharing context with subagents.
- [COMMAND_EXECUTION]: The skill utilizes a structured ExecutionProxy Interface with the 'rtk' prefix to perform terminal actions such as 'rtk npm test'. This interface manages the execution of commands required for the TDD gating process within the agent's environment.
Audit Metadata