prospect-scraper
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from untrusted external sources using LLMs, creating a potential surface for indirect prompt injection. 1. Ingestion points: External websites, Socrata datasets, and business directories (SKILL.md, source-playbook.md). 2. Boundary markers: Not explicitly defined in the processing instructions. 3. Capability inventory: The output is used to drive downstream automated outreach via the companion outbound-engine skill. 4. Sanitization: The skill does not describe specific sanitization steps for the data extracted from web pages.
- [EXTERNAL_DOWNLOADS]: The skill identifies and recommends the use of several external open-source libraries for data processing.
- Includes well-known libraries such as sodapy, edgartools, crawl4ai, firecrawl, and llm-scraper.
- These are established tools used for their intended purposes, such as interacting with government APIs and performing structured data extraction.
Audit Metadata