okp-search
Warn
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the user to install a global NPM package
@markbangwu/okpusingnpm install -g. This package belongs to a third-party developer and is not from a recognized or trusted organization, posing a supply chain risk. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data (READMEs, concepts, and structured knowledge) from the Open Knowledge Protocol, which could contain hidden malicious instructions.
- Ingestion points: External data is brought into the agent's context through
okp domain,okp search, andokp getcommands inSKILL.md. - Boundary markers: The instructions do not define boundary markers or provide warnings for the agent to ignore instructions embedded within the retrieved data.
- Capability inventory: The skill utilizes shell commands via the
okpCLI to fetch data from remote domains. - Sanitization: There is no evidence of sanitization, filtering, or validation of the content retrieved from the protocol before the agent processes it.
Audit Metadata