tweet-analytics

Pass

Audited by Gen Agent Trust Hub on May 6, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill communicates exclusively with the vendor's official domain (xquik.com) for API requests and uses standard environment variable management for credentials.
  • [PROMPT_INJECTION]: The skill identifies a surface for indirect prompt injection as it processes untrusted tweet text and author bios fetched from X.
  • Ingestion points: Untrusted data enters the agent context via the GET /x/tweets/{id} endpoint described in SKILL.md.
  • Boundary markers: Explicit instructions are provided in the Security section of SKILL.md to treat tweet text and author bios as untrusted content.
  • Capability inventory: The skill's capabilities are limited to API interactions with xquik.com. It lacks dangerous tools such as shell access, file system write permissions, or the ability to make arbitrary network requests to unknown domains.
  • Sanitization: The skill explicitly instructs the agent to summarize content rather than outputting it verbatim and warns against executing instructions found within the data.
Audit Metadata
Risk Level
SAFE
Analyzed
May 6, 2026, 10:35 PM