bycrawl-docs

Pass

Audited by Gen Agent Trust Hub on Mar 8, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill uses the WebFetch tool to retrieve documentation pages from https://bycrawl.com. This behavior is expected for a documentation fetcher and targets the official domain of the service it supports.\n- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it ingests content from external web pages.\n
  • Ingestion points: Content is fetched from bycrawl.com/en/docs/ via the WebFetch tool.\n
  • Boundary markers: No explicit delimiters or instructions to ignore embedded commands are included in the retrieval logic.\n
  • Capability inventory: The skill is limited to information retrieval and display; it lacks capabilities for file-write operations, shell execution, or network exfiltration of sensitive data.\n
  • Sanitization: Fetched content is presented directly to the agent without specific filtering or sanitization steps.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 8, 2026, 05:00 PM