kineti-fe-types-sync
Pass
Audited by Gen Agent Trust Hub on Nov 5, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes shell commands using
pnpmfor installation and code generation,gitfor repository management, and theawsCLI for identity verification. These operations are necessary for the synchronization task and are limited to project-local scripts and specific environment profiles. - [EXTERNAL_DOWNLOADS]: The skill fetches data from remote repositories and branches to obtain the latest backend contract definitions (OpenAPI and WebSocket schemas). This is a core requirement of the synchronization workflow.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted input from external schema files, creating a potential surface for indirect prompt injection.
- Ingestion points: External data is read from
openapi.json,ws_models.json, and repository-level instructions as defined inSKILL.md. - Boundary markers: The skill does not implement explicit boundary markers or delimiters for the ingested schema data.
- Capability inventory: The agent has the capability to execute shell commands (
pnpm,aws,git), write to the filesystem, and access the network for repository updates. - Sanitization: There are no explicit instructions for sanitizing or validating the contents of the ingested schemas before processing.
Audit Metadata