x-thread-fetcher
Pass
Audited by Gen Agent Trust Hub on Apr 7, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: Indirect prompt injection surface identified due to the skill's core functionality of ingesting and analyzing untrusted data from X/Twitter and external outbound links.
- Ingestion points: The skill triggers on and processes x.com and twitter.com URLs, as well as substantive outbound links extracted from those posts.
- Boundary markers: There are no explicit delimiters or instructions provided to the agent to ignore or isolate potential commands embedded within the fetched external content.
- Capability inventory: The skill utilizes the browser, web_fetch, and research-scout tools, giving it broad access to retrieve and interpret remote content.
- Sanitization: The instructions lack requirements for sanitizing, validating, or escaping the retrieved data before it is incorporated into the final summary or analysis.
Audit Metadata