serp-feature-sniper
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to ingest and analyze content from external, untrusted competitor websites via the
fetch_webpagetool and search results viaweb_search. This creates a vulnerability surface for indirect prompt injection attacks. - Ingestion Points: Competitor pages analyzed in Phase 2A and 2B, and SERP result patterns in Phase 1.
- Boundary Markers: Absent. The instructions do not specify the use of delimiters or 'ignore' instructions when processing external HTML/text content.
- Capability Inventory: The agent has capabilities to fetch external webpages, perform web searches, and write report files to the local file system (
clients/<client-name>/seo/). - Sanitization: No explicit instructions are provided for sanitizing or escaping the content fetched from external sources before it is processed by the agent.
- [EXTERNAL_DOWNLOADS]: The skill facilitates and encourages network operations to external third-party SEO services (SerpAPI, Serper.dev, DataForSEO, ValueSERP) to retrieve SERP data. It also fetches arbitrary external content from 'feature holders' to perform formatting analysis.
Audit Metadata