batch-research
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill identifies a potential surface for indirect prompt injection as it ingests external URL sources for processing.
- Ingestion points: Reads data source definitions and URL patterns from the local
.opencode/REFERENCE.mdfile. - Boundary markers: No explicit delimiters or 'ignore' instructions are used to isolate the data source list from the agent's scheduling logic.
- Capability inventory: The skill has the capability to invoke a secondary
researcheragent and write execution logs to thelogs/directory. - Sanitization: Input validation for the URLs and sanitization of the research data are not explicitly performed within this scheduling component.
Audit Metadata