Skills
skills/sundial-org/awesome-openclaw-skills/search-x/Gen Agent Trust Hub

search-x

Fail

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: HIGHDATA_EXFILTRATIONPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [DATA_EXFILTRATION] (HIGH): The script scripts/search.js accesses the sensitive configuration file ~/.clawdbot/clawdbot.json. This file likely contains multiple credentials for the agent environment. Accessing shared credential stores increases the risk of unintended data exposure.
  • [PROMPT_INJECTION] (LOW): The skill is susceptible to Indirect Prompt Injection (Category 8) because it ingests untrusted external data. Evidence: 1. Ingestion points: Untrusted tweet content is fetched from the xAI API in scripts/search.js. 2. Boundary markers: None. The tweet content is printed directly to stdout for the agent to consume without delimiters. 3. Capability inventory: scripts/search.js has network access (https) and file system read access (fs). 4. Sanitization: None. The content is used exactly as returned by the API.
  • [COMMAND_EXECUTION] (LOW): The skill is designed to be executed via node commands, as defined in SKILL.md and package.json.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Feb 17, 2026, 01:51 PM