cli-design
Pass
Audited by Gen Agent Trust Hub on Oct 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill requires the agent to ingest and analyze output from external command-line tools and their source code.
- Ingestion points: SKILL.md instructions for 'Explaining or auditing an existing CLI' involve running help commands and reading command definitions, docs, and scripts.
- Boundary markers: The instructions lack delimiters or specific warnings to ignore potential instructions embedded within the analyzed data.
- Capability inventory: The audit process involves shell command execution and filesystem read access to perform analysis.
- Sanitization: There is no requirement to sanitize or validate the external content before the agent processes it.
Audit Metadata