bus-debugging
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied hardware transaction logs and trace data, which represents a potential ingestion surface for indirect instructions.
- Ingestion points: Analyzes wire captures and transaction evidence as described in
SKILL.md. - Boundary markers: No specific delimiters are defined to isolate user-provided data from instructions.
- Capability inventory: The skill does not include any tools or instructions for network access, file system modification, or shell command execution.
- Sanitization: The instructions do not specify validation or sanitization of the provided hardware traces.
- [EXTERNAL_DOWNLOADS]: The skill provides links to official documentation from trusted technology organizations.
- Evidence: References Zephyr Project and Raspberry Pi documentation in
references/workflow.md.
Audit Metadata