lead-scraper

Pass

Audited by Gen Agent Trust Hub on Jul 30, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill represents a surface for indirect prompt injection. It is designed to ingest and process untrusted data from external websites (scraping leads) and output it into structured formats (CSV).
  • Ingestion points: The skill ingests data from external websites based on user-provided 'region' and 'industry' criteria.
  • Boundary markers: No explicit boundary markers or instructions to ignore embedded commands in the source data are provided in the SKILL.md.
  • Capability inventory: The skill is a set of instructions; it does not include scripts with subprocess, network, or file-write capabilities of its own, though it utilizes the host agent's tools.
  • Sanitization: There is no evidence of sanitization or filtering of the external content before it is processed by the AI.
  • [DATA_EXPOSURE]: The skill explicitly targets the collection of PII/business contact data (Company Name, Contact Person, Phone, Address). While this is the intended purpose for B2B sales, it encourages the handling of sensitive contact information.
  • [NO_CODE]: The skill consists entirely of Markdown instructions and metadata; no executable scripts (.py, .js, .sh) are included in the package.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 30, 2026, 08:04 AM
Security Audit — agent-trust-hub — lead-scraper