skills/carlheath/ogmios/scraping/Gen Agent Trust Hub

scraping

Pass

Audited by Gen Agent Trust Hub on Jul 18, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is designed to ingest and process untrusted data from external websites, which creates a surface for Indirect Prompt Injection attacks.
  • Ingestion points: The skill uses WebFetch, searxng, BrightData, and Playwright to retrieve content from arbitrary user-provided URLs and search results (SKILL.md).
  • Boundary markers: There are no instructions to use XML-style tags, delimiters, or specific 'ignore' instructions when the agent processes the scraped content.
  • Capability inventory: The skill environment is configured with access to tools including Bash (command execution), Playwright (browser navigation/snapshot/evaluate), and WebFetch (network requests).
  • Sanitization: The instructions do not define any filtering, escaping, or validation steps for the content retrieved from external sources before the agent processes it or generates a response.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 18, 2026, 08:08 PM
Security Audit — agent-trust-hub — scraping