whitespark-tool
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill specifies that the agent should interpret external data shared by the user, such as citation gap reports and customer lists, which creates an ingestion point for potentially untrusted content.
- Ingestion points: User-provided citation gap reports and customer lists (SKILL.md).
- Boundary markers: The instructions do not define specific delimiters for separating user data from system instructions.
- Capability inventory: The skill is instructional and suggests manual interpretation or direct REST API calls for data retrieval.
- Sanitization: No specific filtering or validation of user-provided content is defined.
Audit Metadata