geo-platform-optimizer
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to analyze content from a user-specified target URL. This creates a surface where malicious instructions embedded in the external site could potentially influence the agent's analysis or report generation.
- Ingestion points: The external target URL mentioned in the 'How to Use This Skill' section of SKILL.md.
- Boundary markers: The skill lacks explicit instructions for the agent to use delimiters or to disregard potential instructions contained within the external content.
- Capability inventory: The skill requires the agent to read external web data and write a resulting markdown file (GEO-PLATFORM-OPTIMIZATION.md).
- Sanitization: There are no instructions for sanitizing or filtering the content retrieved from the external URL before it is processed.
Audit Metadata