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
ReadandWebFetchtools 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, andGlobtools. - 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