x-api-v2

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • Indirect Prompt Injection (LOW): The skill documents an interface for ingesting untrusted data from the X platform, which presents a potential surface for indirect prompt injection attacks.\n
  • Ingestion points: Operations like getDirectMessagesEvents.md and getPostsById.md allow the agent to read content authored by external, untrusted users.\n
  • Boundary markers: The documentation does not specify the use of delimiters, structured data enforcement, or "ignore embedded instructions" warnings when handling retrieved social media content.\n
  • Capability inventory: The skill provides access to high-impact write capabilities that could be abused if an injection is successful, including createPosts.md (tweeting), followUser.md, and deletePosts.md.\n
  • Sanitization: No sanitization, escaping, or validation logic for the external content is described within the documentation files, leaving the responsibility for safety entirely to the agent's implementation.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:27 PM