web-scraper
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- Prompt Injection (LOW): Indirect prompt injection surface detected.
- Ingestion points: Untrusted content is ingested from external websites via
scripts/main.py. - Boundary markers: Absent. The documentation does not provide delimiters or instructions for the agent to ignore commands within scraped data.
- Capability inventory: The skill uses
requestsandbeautifulsoup4to retrieve and parse content, which is then handled by the agent. - Sanitization: Absent. No evidence of content sanitization or filtering is provided in the skill instructions.
- External Downloads (SAFE): The skill requires standard Python packages (beautifulsoup4, requests, pandas, click, lxml) from PyPI, which is considered a safe and standard practice for this functionality.
Audit Metadata