x-api

Pass

Audited by Gen Agent Trust Hub on Aug 15, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill allows the agent to ingest external data from X (Twitter) via search and timeline endpoints, which represents a potential surface for indirect prompt injection from third-party content.
  • Ingestion points: Untrusted data enters the agent context via API responses from api.x.com as shown in SKILL.md.
  • Boundary markers: The example code does not include specific delimiters or instructions to ignore embedded commands within the retrieved tweets.
  • Capability inventory: The skill demonstrates network request capabilities and local file reading for media uploads.
  • Sanitization: No sanitization or validation logic is implemented in the provided Python snippets to filter retrieved content.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 15, 2026, 03:24 AM
Security Audit — agent-trust-hub — x-api