ai-search-optimization
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists of purely instructional documentation regarding Generative Engine Optimization (GEO) and Answer Engine Optimization (AEO). It provides a framework for structuring content to be citable by AI agents and does not contain any executable scripts or high-risk command patterns.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external content provided through the
target_page_or_topicandcurrent_content_or_briefinputs. - Ingestion points: Untrusted data is ingested via inputs defined in
contract.yaml. - Boundary markers: The instructions do not define explicit delimiters to isolate external content from the agent's system instructions.
- Capability inventory: No dangerous capabilities such as file system writes, network operations to arbitrary domains, or subprocess execution are present in the skill's definitions.
- Sanitization: No explicit sanitization or filtering of external content is defined, but the lack of executable capabilities mitigates the associated risks.
Audit Metadata