okp-import
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill reads and processes external domain README files to define schemas and 'distill' knowledge concepts. This creates a surface where malicious instructions embedded in these external sources could influence agent behavior.\n
- Ingestion points: The skill reads domain README files using the
okp domain <domain>command to determine field requirements and formatting rules.\n - Boundary markers: There are no explicit delimiters or instructions provided to the agent to distinguish between administrative instructions and untrusted content from the README files.\n
- Capability inventory: The skill has access to network-based write operations through the
okp putandokp batchcommands, allowing it to modify data in the target protocol.\n - Sanitization: The workflow does not describe any sanitization, filtering, or validation steps for content extracted from the external domain documents before they are processed by the agent.\n- [EXTERNAL_DOWNLOADS]: The skill requires the installation of the
@markbangwu/okpCLI tool from the NPM registry. While this is a common requirement for specialized tools, users should verify the provenance of third-party packages.
Audit Metadata