serpapi-core-workflow-a

Pass

Audited by Gen Agent Trust Hub on Sep 11, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes untrusted data from external search results via SerpApi, which creates a surface for indirect prompt injection attacks.
  • Ingestion points: Data is fetched from the SerpApi search engine in SKILL.md (Step 1-4) using client.search(). The results include titles, snippets, and answer box content from various websites.
  • Boundary markers: The implementation does not include specific delimiters or instructions to the agent to ignore embedded commands within the search results.
  • Capability inventory: The skill's configuration in SKILL.md allows the use of high-privilege tools including Read, Write, Edit, Bash(npm:*), and Grep.
  • Sanitization: There is no evidence of sanitization, filtering, or validation of the search result content before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 11, 2026, 08:40 AM
Security Audit — agent-trust-hub — serpapi-core-workflow-a