web-search-techniques

Pass

Audited by Gen Agent Trust Hub on May 10, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides guidelines for using a local Python script (webfetch.py) via the command line to retrieve web content when standard scraping tools are blocked.
  • [EXTERNAL_DOWNLOADS]: The skill's primary function involves retrieving information from external websites, which is standard for research tasks.
  • [PROMPT_INJECTION]: The skill processes data from external websites, which is a known surface for indirect prompt injection. This is considered acceptable and safe given the skill's primary research purpose.
  • Ingestion points: Web content fetched from arbitrary URLs via WebFetch or the webfetch.py script.
  • Boundary markers: The provided instructions do not specify any delimiters or safety markers for separating fetched content from the agent's instructions.
  • Capability inventory: The skill uses the Bash tool to execute a Python script for data retrieval.
  • Sanitization: No content sanitization or validation steps are outlined in the instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
May 10, 2026, 03:15 AM