sales-outscraper
Pass
Audited by Gen Agent Trust Hub on Apr 4, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill instructions and reference materials are benign and align with the stated goal of providing help for the Outscraper platform. No signs of obfuscation, persistence, or data exfiltration were found.
- [EXTERNAL_DOWNLOADS]: The documentation references the official Outscraper Python SDK (
pip install outscraper) for interacting with the platform's API. - [PROMPT_INJECTION]: The skill facilitates the ingestion of untrusted external data by providing instructions for scraping content such as Google Maps reviews and Amazon product data. While no active injection is present, this constitutes a surface for indirect prompt injection if the agent processes the retrieved data without sanitization. Ingestion points: Scraping endpoints defined in
outscraper-api-reference.md. Boundary markers: Absent. Capability inventory: Data extraction and potential export to CRMs or other tools. Sanitization: Not explicitly mentioned in the instructions.
Audit Metadata