ieee-journal-browse
Pass
Audited by Gen Agent Trust Hub on Mar 15, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface because it ingests untrusted data from a third-party website (IEEE Xplore).
- Ingestion points: Data is collected from page headers, body text, and links via
evaluate_scriptinSKILL.md. - Boundary markers: None. The scraped content (titles, metrics) is interpolated directly into the response template in Step 3.
- Capability inventory: The skill uses
navigate_pageandevaluate_scripttools. - Sanitization: No filtering or sanitization of the external web content is performed.
- [COMMAND_EXECUTION]: The skill utilizes browser-side script execution to navigate and scrape pages.
- Evidence: The
initScriptinSKILL.mdcontains code (Object.defineProperty(navigator, 'webdriver', {get: () => undefined})) designed to modify browser properties to evade anti-bot detection.
Audit Metadata