astcount-refactor-interactive
Pass
Audited by Gen Agent Trust Hub on Aug 29, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the agent to download and run the
astcounttool (version 0.3.0) usingnix,bunx, ornpx. These resources are hosted on GitHub (github:wokalski/astcount) and the NPM registry. Since these resources are owned by the skill's author, this is a standard delivery mechanism for the tool's functionality. - [COMMAND_EXECUTION]: The skill involves executing shell commands to run the
astcounttool and to perform formatting and testing on the codebase being refactored. This behavior is necessary for the skill's primary purpose but represents a capability to execute code in the user's environment. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external codebases, which creates a surface for indirect prompt injection.
- Ingestion points: Source code files within the specified project scope (SKILL.md).
- Boundary markers: Absent; there are no specific instructions to treat the analyzed code as data only or to ignore embedded instructions.
- Capability inventory: File system read/write access, execution of the
astcountbinary, and execution of arbitrary project test suites (SKILL.md). - Sanitization: Absent; the skill does not mention sanitizing or validating the contents of the code files before they are processed by the agent or the underlying tools.
Audit Metadata