watch
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to track external sources such as research papers, updates, and specific fields, creating a potential vector where instructions embedded in those external sources could influence the agent's behavior.
- Ingestion points: Processes external research papers, web updates, and field monitoring data as indicated in the description.
- Boundary markers: No specific boundary markers or 'ignore embedded instructions' prompts are defined in the skill instructions to delimit untrusted content.
- Capability inventory: The skill writes research baselines to the
outputs/directory and interacts with scheduling tools. - Sanitization: No sanitization or validation of the monitored external data is specified.
Audit Metadata