Li
Pass
Audited by Gen Agent Trust Hub on Nov 3, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill acts as an organizational layer that maps user phrases to specific internal commands (slash commands) within the agent environment.
- [NO_CODE]: No executable logic, scripts, or system-level commands are present in the provided file. It consists entirely of markdown instructions and routing tables.
- [INDIRECT_PROMPT_INJECTION]: While the skill processes user-provided natural language to perform routing decisions, it lacks dangerous capabilities—such as network access or file system modification—that could be exploited via adversarial inputs. Evidence: User input is ingested at the prompt level to determine routing, but no sanitization or boundary markers are used, which is acceptable given the lack of high-privilege tools.
- [DATA_EXPOSURE_AND_EXFILTRATION]: No network operations, hardcoded credentials, or sensitive file path references were detected in the skill content.
Audit Metadata