skills/milkywayrules/dioilham-skills/dio-dont-trust-your-memory-check-the-docs-first/Gen Agent Trust Hub
dio-dont-trust-your-memory-check-the-docs-first
Pass
Audited by Gen Agent Trust Hub on Jul 22, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill contains no executable code, scripts, or system-level commands. All content consists of natural language instructions for the agent's operational logic.
- [PROMPT_INJECTION]: The skill instructs the agent to ingest untrusted data from external sources (websites and documentation). Ingestion points: external URLs fetched during the 'Verify' step. Boundary markers: none specified in the instructions. Capability inventory: textual responses and citations only; no command execution or file system access. Sanitization: none specified. The risk of exploitation is negligible due to the lack of dangerous capabilities.
Audit Metadata