pr-media-monitor
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes content from external, untrusted sources including news outlets, Twitter, and LinkedIn, which creates a surface for indirect prompt injection attacks where data may contain malicious instructions.
- Ingestion points: Data enters the agent's context through tools like
google_news_bulk_articles,tavily_search,twitter_web_search_timeline, andlinkedin_web_v2_user_postsas described inSKILL.md. - Boundary markers: The instructions do not specify the use of delimiters or specific warnings to ignore instructions embedded within the retrieved media content.
- Capability inventory: The skill utilizes
sandbase_call_toolto fetch information; it does not exhibit capabilities for file writing, system modification, or non-research network operations. - Sanitization: No explicit sanitization or filtering logic is defined for the data retrieved from external platforms before it is synthesized by the agent.
Audit Metadata