blog-geo

Pass

Audited by Gen Agent Trust Hub on Feb 26, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it is designed to fetch and process untrusted text from external blog posts or local files.
  • Ingestion points: Step 1 utilizes the Read and WebFetch tools to extract content from files or URLs.
  • Boundary markers: The instructions do not define clear delimiters or specify that the agent should ignore instructions embedded within the blog post content during analysis.
  • Capability inventory: The skill has access to Read, Write, WebFetch, Grep, and Glob tools.
  • Sanitization: There is no logic provided to sanitize, escape, or validate the ingested content before it is processed by the AI for scoring and report generation.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 26, 2026, 11:10 PM