x
Pass
Audited by Gen Agent Trust Hub on Apr 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to use the
xurlCLI tool for shell commands to interact with the Twitter API, including profile lookups and searches. - [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection as it ingests and processes untrusted data from X.
- Ingestion points: Data from tweets, timelines, and user bios enters the agent context through
xurlcommand outputs (SKILL.md). - Boundary markers: No delimiters or isolation instructions are provided to separate external tweet content from the agent's core instructions.
- Capability inventory: The agent can execute shell commands via
xurland handle sensitive authentication tokens ($X_TOKEN). - Sanitization: There is no evidence of sanitization or validation of the retrieved tweet content before it is parsed by the agent.
Audit Metadata