car-advisor
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [NO_CODE]: The skill consists entirely of natural language instructions and documentation in Markdown format. There are no scripts, binaries, or executable configuration files included in the package.
- [SAFE]: No malicious patterns such as prompt injection, data exfiltration, or obfuscation were detected. The skill's behavior is consistent with its stated purpose of providing car buying and maintenance advice.
- [INDIRECT_PROMPT_INJECTION]: The skill defines an interaction model that processes untrusted user input (e.g., budget, vehicle usage, car models). While this represents a theoretical ingestion surface, the risk is negligible because the skill does not possess any capabilities (such as network access, file system modification, or command execution) that could be exploited.
- Ingestion points: User-supplied car preferences and financial details (SKILL.md).
- Boundary markers: None identified.
- Capability inventory: None; the skill is purely informational.
- Sanitization: None identified.
Audit Metadata