v-device-debug
Pass
Audited by Gen Agent Trust Hub on Nov 15, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill describes a legitimate software development and debugging workflow for remote devices where direct access is unavailable.
- [DATA_EXFILTRATION]: While the skill involves exposing a local server via a tunnel to deliver artifacts to a user, it includes explicit instructions to ensure that diagnostic messages are 'secrets-free'. The workflow is designed for user-authorized delivery of development builds.
- [INDIRECT_PROMPT_INJECTION]: The skill handles untrusted user input in the form of screenshots. It mitigates potential risks by instructing the agent to transcribe text literally and verify root causes against official source code and documentation rather than relying on potentially poisoned error messages or comments.
Audit Metadata