skills/harehare/mq/web-scraping/Gen Agent Trust Hub

web-scraping

Pass

Audited by Gen Agent Trust Hub on Aug 11, 2026

Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is designed to ingest and process data from external, untrusted web pages, which presents a risk of Indirect Prompt Injection if that content contains malicious instructions.
  • Ingestion points: Data is fetched from URLs using mq-crawl or the http() function described in SKILL.md.
  • Boundary markers: The instructions do not provide guidance on using delimiters or safety warnings to ensure the agent ignores instructions embedded within the scraped data.
  • Capability inventory: The agent can execute shell commands (mq, mq-crawl) and make network requests.
  • Sanitization: There is no evidence of sanitization or filtering of the external content before it is processed by the agent.
  • [DATA_EXFILTRATION]: The skill enables network communication to arbitrary external domains, including support for POST requests and custom headers via the http() function. This capability can be used to transmit data to external servers.
  • [COMMAND_EXECUTION]: The skill relies on executing CLI tools (mq and mq-crawl) to fetch, crawl, and transform web content.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 11, 2026, 06:35 AM
Security Audit — agent-trust-hub — web-scraping