generate-news-x-posts
Pass
Audited by Gen Agent Trust Hub on Nov 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted news content and search results from the internet to generate social media posts, creating a potential surface for adversarial data to influence the agent's behavior.
- Ingestion points: Web content retrieved via Brave News/Web Search, DuckDuckGo HTML, and user-provided news URLs as described in SKILL.md.
- Boundary markers: No explicit delimiters or boundary markers are defined to isolate fetched news content from the agent's core instructions.
- Capability inventory: The skill does not utilize subprocesses, file-writing tools, or network exfiltration capabilities; it is limited to generating text for user review.
- Sanitization: The instructions mandate fact-checking against reliable sources and verifying publication dates, which serves as a manual validation step.
- [EXTERNAL_DOWNLOADS]: The skill references a configuration file (config/v3.json) from the official Twitter GitHub repository for character count validation. This is a functional reference to a well-known and established service.
Audit Metadata