newsworthiness-check
Pass
Audited by Gen Agent Trust Hub on Oct 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted data provided by users, including news hooks, PR pitch descriptions, and external content from social media or search tools.
- Ingestion points: The skill processes user-supplied text for event newsjacking and pitch evaluation as described in SKILL.md.
- Boundary markers: The instructions do not define specific delimiters (such as XML tags or unique string markers) to separate untrusted user input from the agent's internal evaluation logic.
- Capability inventory: The skill interacts with external tools like news-search and facilitates downstream actions such as generating reactive comments or checking journalist fit.
- Sanitization: While the skill enforces Hard Rules and Sanity Checks to maintain scoring objectivity, it lacks explicit technical sanitization for content interpolated into the prompt.
Audit Metadata