dataforseo-serp-api

Warn

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: MEDIUMDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • PROMPT_INJECTION (MEDIUM): Detected potential for Indirect Prompt Injection (Category 8) due to the processing of untrusted external content.
  • Ingestion points: The skill fetches data from api.dataforseo.com, including search results, snippets, and HTML source code from various search engines (Google, Bing, YouTube).
  • Boundary markers: Absent. The instructions do not guide the agent to use delimiters or ignore instructions found within the retrieved search data.
  • Capability inventory: The skill allows the agent to perform network requests and process retrieved data for summarizing or decision-making. If the output is used to drive subsequent actions, the risk increases.
  • Sanitization: Absent. There is no mention of filtering or sanitizing the retrieved search content before the agent processes it.
  • DATA_EXFILTRATION (LOW): The skill performs network operations to non-whitelisted domains.
  • Evidence: Instructions explicitly require outbound access to api.dataforseo.com and sandbox.dataforseo.com using HTTP Basic Authentication. While legitimate for the skill's purpose, this is a required observation for network-capable skills.
  • CREDENTIALS_UNSAFE (SAFE): No hardcoded credentials were found. The skill uses environment variable placeholders ${DATAFORSEO_LOGIN} and ${DATAFORSEO_PASSWORD} in its examples.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 06:00 AM