dbs-content-risk-check
Pass
Audited by Gen Agent Trust Hub on Aug 12, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill operates as a passive risk assessment tool that evaluates user-provided text, images, and links. It follows a structured workflow to identify potential audit triggers without executing dangerous commands, accessing sensitive system files, or attempting to persist across sessions.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted user-submitted materials, creating a surface for indirect prompt injection.
- Ingestion points: User-provided text, images, and URLs submitted for risk evaluation as defined in the 'Working Tasks' section of SKILL.md.
- Boundary markers: The skill does not employ explicit delimiters or instruction-isolation markers for user data.
- Capability inventory: Content analysis (text and vision) and network access for link verification when requested by the user.
- Sanitization: No specific input sanitization or validation logic is defined in the instructions.
Audit Metadata