guided-config
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill allows the agent to ingest external content which could contain hidden malicious instructions.
- Ingestion Point: In Step 1, the agent explicitly requests documentation URLs from the user to guide the setup process.
- Boundary Markers: The instructions do not include specific delimiters or warnings to the agent to ignore or isolate instructions found within the external documentation.
- Capability Inventory: The skill generates shell commands and configuration file modifications for the user to execute manually based on the ingested context.
- Sanitization: There is no requirement for the agent to validate or sanitize the content extracted from external URLs before presenting instructions to the user.
Audit Metadata