audit-dialogue-subtext
Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze user-provided dialogue scripts. This creates a surface for indirect prompt injection if the ingested text contains instructions meant to influence the agent's behavior. However, this is a low-risk analytical skill with no dangerous capabilities.
- Ingestion points: User-provided dialogue scripts (SKILL.md).
- Boundary markers: No explicit boundary markers or 'ignore embedded instructions' warnings are provided for the processed text.
- Capability inventory: The skill has no capabilities for file system access, network requests, or shell command execution.
- Sanitization: No sanitization of user input is specified.
Audit Metadata