twitter-article-reader

Pass

Audited by Gen Agent Trust Hub on Apr 6, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the agent to fetch content via r.jina.ai, which is a well-known service used for converting web pages into clean markdown format.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes untrusted data from external Twitter/X articles.
  • Ingestion points: Data enters the agent's context via the web_fetch tool when retrieving content from constructed jina.ai URLs (SKILL.md).
  • Boundary markers: The instructions do not specify the use of delimiters (e.g., XML tags or triple backticks) to isolate the external content from the agent's system instructions.
  • Capability inventory: The skill utilizes network capabilities via the web_fetch tool to access external sites.
  • Sanitization: There is no evidence of content validation, escaping, or filtering applied to the retrieved markdown before it is presented to the agent or the user.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 6, 2026, 03:26 AM