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) usingclient.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.mdallows the use of high-privilege tools includingRead,Write,Edit,Bash(npm:*), andGrep. - Sanitization: There is no evidence of sanitization, filtering, or validation of the search result content before it is processed by the agent.
Audit Metadata