geo-crawlers

Pass

Audited by Gen Agent Trust Hub on Feb 27, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through the ingestion and processing of untrusted external content.
  • Ingestion points: The skill uses WebFetch to retrieve robots.txt files, HTML meta tags, and HTTP headers from arbitrary user-provided domains.
  • Boundary markers: Absent. The instructions do not specify the use of delimiters or provide the agent with instructions to ignore commands embedded in the fetched external data.
  • Capability inventory: The skill allows the use of powerful tools including Bash, Write, and WebFetch, which could be misused if an injection is successful.
  • Sanitization: Absent. No explicit validation, escaping, or filtering of the external content is described before the agent processes the data.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 27, 2026, 01:01 PM