cli-power-tools
Pass
Audited by Gen Agent Trust Hub on Feb 27, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill defines patterns for executing powerful CLI operations including in-place file modification using
sed -iand recursive command execution (such as file deletion) via thefd -xandxargspatterns. - [EXTERNAL_DOWNLOADS]: Documents the installation of various Rust-powered utilities through established package managers like Homebrew, APT, and Cargo. These references point to official repositories and well-known software tools.
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface (Category 8) due to its primary function of processing external data.
- Ingestion points: Any file, codebase, or log stream analyzed by tools like
ripgrep,jq,bat, ornushell(referenced inSKILL.mdandreferences/modern-unix-toolbox.md). - Boundary markers: Absent; the instructions do not provide delimiters or warnings for the agent to ignore potentially malicious instructions embedded in the data being processed.
- Capability inventory: The skill enables significant system impact through file-writing (
sed), file-deletion (rm), network requests (xh,http), and arbitrary command execution (fd -x). - Sanitization: Absent; there is no guidance on escaping or validating external content before it is processed or used in pipelines.
Audit Metadata