geo-content-optimizer
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided content for optimization, creating a surface for indirect prompt injection where malicious instructions embedded in the data could potentially influence the agent's behavior.
- Ingestion points: The skill accepts content inputs for optimization as seen in the usage instructions in SKILL.md.
- Boundary markers: No specific delimiters or boundary markers are defined to isolate the content being optimized from the agent's internal logic.
- Capability inventory: The skill relies on platform-side workflows (workflowId: see-workflow-mapping) and does not include local executable scripts or code.
- Sanitization: No sanitization or filtering logic for external content is documented in the provided skill files.
Audit Metadata