lead-enrichment
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill interacts with the vendor's official API (api.webclaw.io) to perform its core functions. These network operations are intended, transparently documented, and limited to transmitting company URLs for public data extraction.
- [INDIRECT_PROMPT_INJECTION]: This skill possesses a surface for indirect prompt injection because it processes content from third-party websites. However, the risk is assessed as safe due to the structured JSON-schema-based extraction process and the lack of high-risk capabilities like arbitrary command execution.
- Ingestion points: Data from external listing pages and company sites is ingested into the local environment via scripts/find.py and scripts/enrich.py.
- Boundary markers: The skill does not explicitly define delimiters or instruction-ignore markers for the AI agent when it summarizes the enriched CSV data.
- Capability inventory: The skill has permission to perform network requests to the vendor API and write results to local CSV files.
- Sanitization: The scripts utilize a csv_safe function to prepend characters to cell values starting with formula-triggering prefixes (=, +, -, @), effectively neutralizing CSV injection risks for users opening the data in spreadsheet applications.
Audit Metadata