thought-leadership-monitor
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze content from third-party social media platforms, which introduces a risk of indirect prompt injection.\n
- Ingestion points: External data from LinkedIn, Twitter, and YouTube retrieved using
sandbase_call_tool.\n - Boundary markers: The instructions lack explicit boundary markers or delimiters to separate untrusted content from internal logic.\n
- Capability inventory: The skill utilizes
sandbase_call_toolfor data acquisition and subsequent information synthesis.\n - Sanitization: There are no requirements or steps provided for sanitizing or filtering external content before it is processed by the agent.
Audit Metadata