threads-net-api

Pass

Audited by Gen Agent Trust Hub on Sep 3, 2026

Risk Level: SAFE
Full Analysis
  • [DATA_EXPOSURE]: The skill facilitates network communication with api.scavio.dev (the vendor's official domain) to retrieve public social media data. It uses an API key (SCAVIO_API_KEY) for authentication, which is handled via environment variables or headers, following security best practices.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data from Threads (posts, replies, and profile descriptions).
  • Ingestion points: Data enters the agent's context through several endpoints such as /threads/profile, /threads/user/posts, and /threads/post/comments (SKILL.md).
  • Boundary markers: No specific boundary markers or instructions to ignore embedded commands are present in the documentation.
  • Capability inventory: The skill primarily performs read operations and does not possess capabilities like arbitrary command execution, file system writes, or secondary network exfiltration that could be triggered by malicious content in a post.
  • Sanitization: The instructions do not specify content sanitization, but they do provide guardrails against data fabrication and attribution loss.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 3, 2026, 12:23 PM
Security Audit — agent-trust-hub — threads-net-api