claudish-usage
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTIONPRIVILEGE_ESCALATION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides numerous examples of shell commands involving the
claudishCLI, including installation (npm install -g claudish) and execution (claudish --model <model> "task"). These commands enable interaction with external AI services. - [EXTERNAL_DOWNLOADS]: Recommends downloading and installing the
claudishpackage from public registries (NPM or Bun). - [PRIVILEGE_ESCALATION]: Notes the availability of a
--dangerousflag for the CLI, which is documented to disable internal sandboxing mechanisms. - [INDIRECT_PROMPT_INJECTION]: The skill defines workflows that ingest external data and process it through third-party models, creating a potential injection surface.
- Ingestion points: Data enters the environment via file reads and standard input passed to the
claudishCLI inSKILL.md. - Boundary markers: The skill advocates for a 'File-Based Sub-Agent Pattern' using markdown templates to structure and separate data.
- Capability inventory: The instruction set utilizes
Bash,Write,Read, andTasktools. - Sanitization: No specific output sanitization or filtering is defined beyond requested markdown formatting.
Audit Metadata