x-knowledge
Pass
Audited by Gen Agent Trust Hub on Sep 26, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill is designed to execute various subcommands of the
x-cmdCLI tool (e.g.,x hn,x wkp,x ddgo,x rfc,x gtb,x se). These commands are used to interact with external knowledge services and process information locally. - [INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection as it retrieves data from untrusted external sources.
- Ingestion points: Data enters the agent context through search results and article content fetched from Hacker News, Wikipedia, DuckDuckGo, RFC documents, Project Gutenberg, and Stack Exchange via the
SKILL.mdinstructions. - Boundary markers: There are no explicit instructions or delimiters provided to the agent to treat the retrieved content as untrusted or to ignore instructions embedded within the search results.
- Capability inventory: The skill facilitates command execution through the
x-cmdCLI, including network operations and local data processing. - Sanitization: No sanitization, filtering, or validation of the retrieved external content is specified before it is processed by the agent.
Audit Metadata