serpapi

Fail

Audited by Snyk on Mar 7, 2026

Risk Level: HIGH
Full Analysis

HIGH W007: Insecure credential handling detected in skill instructions.

  • Insecure credential handling detected (high risk: 0.90). The prompt’s examples and helper scripts embed the API key directly into URLs and curl commands (api_key={apiKey} / &api_key=$API_KEY), which requires the agent to include secret values verbatim in requests or generated commands.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches live Google search results via SerpAPI (e.g., curl calls in SKILL.md and scripts/search.sh) and ingests organic_results/snippets from arbitrary public websites which the agent is intended to read and use to make decisions, so untrusted third‑party content could inject instructions that affect behavior.
Audit Metadata
Risk Level
HIGH
Analyzed
Mar 7, 2026, 07:32 AM