new-vertical
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to scrape and process data from external, third-party websites such as government registries and tax portals.
- Ingestion points: Phase 3 ("Scrape & ingest") involves collecting data from authoritative external sources.
- Boundary markers: The skill does not specify the use of delimiters or provide instructions to the agent to ignore potential malicious prompts embedded within the scraped content.
- Capability inventory: The skill utilizes Python (
curl_cffi), external scraping tools (/scrapling), and file system operations to archive and transform data. - Sanitization: While Phase 4 mentions data cleaning (deduplication and normalization), there is no mention of security-focused sanitization to prevent the agent from executing instructions found in the scraped data.
Audit Metadata