trend-scout
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill operates within expected parameters to perform its stated function of gathering and summarizing trending topics. It utilizes explicitly allowed tools for search and workspace file management.
- [INDIRECT_PROMPT_INJECTION]: The skill represents a surface for indirect prompt injection as it processes data from external sources, which is inherent to its primary purpose.
- Ingestion points: Fetches external content via the get_trending MCP tool and WebSearch (SKILL.md).
- Boundary markers: The instructions do not define specific delimiters or instructions for the agent to ignore adversarial content within trend data.
- Capability inventory: The skill utilizes the Write tool to store trend snapshots in the local workspace (SKILL.md).
- Sanitization: No specific filtering or sanitization of external results is detailed beyond the summarization step performed by the model.
Audit Metadata