skill-navigator
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [NO_CODE]: The skill does not include any scripts, executable code, or package dependencies. It consists entirely of natural language instructions for the agent.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied task descriptions to provide recommendations. 1. Ingestion points: User descriptions of tasks and goals provided at runtime. 2. Boundary markers: None. 3. Capability inventory: Limited to text generation; no tools, subprocess calls, or file system access are utilized. 4. Sanitization: None.
- [SAFE]: No malicious patterns such as direct prompt injection, data exfiltration, or obfuscation were detected. The skill is designed purely as an informational guide.
Audit Metadata