x-analytics
Pass
Audited by Gen Agent Trust Hub on Mar 22, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill ingests and processes untrusted content from X/Twitter posts, which creates a surface for indirect prompt injection attacks.
- Ingestion points: Untrusted tweet data is ingested via the javascript_tool and read_page tools in SKILL.md.
- Boundary markers: There are no explicit markers or instructions to isolate the scraped content from the agent's internal reasoning or instructions.
- Capability inventory: The skill possesses the capability to execute JavaScript in the browser and write data to the local file system (e.g., content-performance.md).
- Sanitization: The extraction script performs basic truncation of tweet text to 80 characters but lacks robust sanitization to prevent the interpretation of instructions hidden within the scraped text.
- [COMMAND_EXECUTION]: The skill provides and executes custom JavaScript code blocks using the javascript_tool to interact with and scrape data from the web browser.
Audit Metadata