make-scenario-explore
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external Make scenarios, organizations, and modules, creating a surface for indirect prompt injection if those sources contain malicious instructions.
- Ingestion points: Data enters the agent's context through tools such as
environment_get,scenario_list, andscenario_getwhich query the Make API. - Boundary markers: There are no explicit instructions for the agent to use delimiters or ignore embedded instructions within the fetched scenario data.
- Capability inventory: Although this skill is read-only, the broader agent environment referenced (
make-scenario-operations,make-scenario-building) contains tools for execution and modification. - Sanitization: The instructions do not define sanitization, validation, or escaping procedures for the content retrieved from the Make platform.
Audit Metadata