okp-search
Warn
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill requires the global installation of a specific third-party npm package:
@markbangwu/okp. This package is necessary for the CLI toolokpto function. - [COMMAND_EXECUTION]: The primary function of the skill is to execute the
okpbinary with various flags (e.g.,search,domains,sample,get,links). This involves running shell commands to interact with an external API. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to fetch external content (concept bodies, READMEs, and metadata) from the Open Knowledge Protocol using
okp get <id>andokp domain <domain>. - Ingestion points: Data enters the agent context through CLI output from the
okptool. - Boundary markers: The instructions do not specify the use of delimiters or specific sanitization rules to differentiate between trusted instructions and the external knowledge content retrieved.
- Capability inventory: The skill has the ability to execute CLI commands and read from external knowledge domains.
- Sanitization: There is no evidence of filtering or escaping content retrieved from the external knowledge domains before it is processed by the agent.
Audit Metadata