dbs-ai-check
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill defines a text-based analysis workflow aimed at detecting AI writing patterns. The instructions focus on linguistic analysis, reporting formats, and conversational guidance.
- [SAFE]: No evidence of prompt injection, data exfiltration, or persistence mechanisms was found. The skill does not attempt to bypass safety guidelines or access restricted system resources.
- [SAFE]: The configuration in
agents/openai.yamlis standard and limited to interface definitions with no suspicious parameters. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted user text for analysis. While it lacks explicit boundary markers (e.g., XML tags) for the input text, the risk is minimal as the agent's capabilities are restricted to text generation; there are no network, file, or command execution tools associated with this skill (Evidence: Ingestion point is user text; Capability inventory is limited to text reporting; Sanitization and boundaries are minimal).
Audit Metadata