dig
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process "new findings" from external targeted searches and merge them into an active research session. This creates a surface for indirect prompt injection if the search results contain adversarial content designed to influence the agent's behavior.
- Ingestion points: External findings from targeted searches are brought into the agent's context (SKILL.md, Workflow steps 3 and 4).
- Boundary markers: There are no explicit instructions to use delimiters or ignore embedded instructions within the fetched data.
- Capability inventory: The skill possesses the ability to merge new findings into existing session data, re-rank reports, and update saved session files.
- Sanitization: No sanitization or validation of the external findings is mentioned before the merge or re-ranking processes.
Audit Metadata