gs-fulltext
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted paper metadata (titles, authors, journal names) from the Google Scholar results page and includes it in a Markdown report. This creates an attack surface where maliciously crafted webpage content could attempt to influence the agent's behavior, although the skill's specific purpose and restricted tools limit the potential impact.
- [DYNAMIC_EXECUTION]: The skill populates a JavaScript template with a paper identifier (data-cid) and executes it via browser automation tools. If the identifier provided to the skill is not sanitized before interpolation into the script string, it could lead to script injection within the browser context.
Audit Metadata