author-standards
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill downloads the
@lutzseverino/repo-standardspackage from the official NPM registry to provide the necessary validation tooling. This is a vendor-owned resource matching the skill author. - [COMMAND_EXECUTION]: The skill executes the downloaded CLI tool and system commands such as
npmandmktempto manage the tool's installation and perform standards validation. - [DYNAMIC_EXECUTION]: The skill generates and executes custom check and fix scripts based on user preferences. This behavior is mitigated by instructions requiring explicit human-in-the-loop review of the generated material and execution within temporary project fixtures using non-shell subprocess calls.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted repository content and authoring notes to derive standards. The risk of indirect prompt injection is addressed by instructions to treat external content as evidence for decision-making rather than direct instructions to follow.
Audit Metadata