x-skill

Pass

Audited by Gen Agent Trust Hub on Jun 17, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill documentation references a prerequisite CLI tool hosted on an external GitHub repository (github.com/xdevplatform/xurl) belonging to a vendor that is not recognized as a pre-approved trusted organization.- [PROMPT_INJECTION]: Indirect Prompt Injection vulnerability surface detected.
  • Ingestion points: The skill retrieves untrusted data from the X API through commands such as xurl search, xurl read, xurl timeline, xurl mentions, and xurl dms (SKILL.md).
  • Boundary markers: The instructions lack explicit directives for the agent to treat output from these commands as untrusted or to ignore any embedded instructions within the fetched data.
  • Capability inventory: The skill provides the agent with several powerful capabilities to modify state, including xurl post, xurl reply, xurl delete, and xurl dm (SKILL.md).
  • Sanitization: There are no requirements or methods specified for sanitizing or validating the external content before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 17, 2026, 07:33 AM
Security Audit — agent-trust-hub — x-skill