serper
Warn
Audited by Snyk on Feb 13, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The skill calls the Serper Google search API and then concurrently fetches and scrapes the actual result pages (web and news URLs) using trafilatura (see scripts/search.py and the README), returning full extracted page text from arbitrary public websites and news sources which are untrusted third‑party content the agent is expected to read.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.90). The skill calls the Serper APIs (https://google.serper.dev/search and https://google.serper.dev/news) at runtime and then fetches and injects the full text of the arbitrary result pages (via trafilatura) into the agent's output context, which can directly control prompts by supplying remote content.
Audit Metadata