dbs-ai-check
Pass
Audited by Gen Agent Trust Hub on Oct 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied text to detect AI writing patterns, which is a standard surface for indirect prompt injection. However, the risk is negligible as the skill has no functional capabilities.
- Ingestion points: Processes user-provided text for scanning as instructed in
SKILL.md. - Boundary markers: Absent; the skill does not define specific delimiters for handling user input.
- Capability inventory: None; the skill has no access to network, filesystem, or shell tools.
- Sanitization: Absent; user text is quoted directly in reports without sanitization.
- [SAFE]: The skill consists entirely of natural language instructions. There are no scripts, binaries, or automated shell commands (such as dynamic context injection) included in the files.
- [SAFE]: No sensitive data access or exfiltration patterns were detected. The skill does not manage credentials or environment variables.
Audit Metadata