doc-it
Pass
Audited by Gen Agent Trust Hub on Jun 30, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes
git logto programmatically retrieve the commit history and merged pull request data from the local repository for the purpose of generating human-readable changelogs. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests untrusted content from local source code and configuration files to automate documentation drafting.
- Ingestion points: Source code files (modules, exports, entry points), configuration files, and existing documentation files within the local repository (SKILL.md).
- Boundary markers: No specific delimiters or instructions to ignore embedded commands are specified for the processing of source files.
- Capability inventory: The skill has the capability to write and modify files within the local repository, specifically targeting READMEs, API documentation, onboarding guides, and changelogs.
- Sanitization: The instructions do not define any sanitization or validation steps to filter potential malicious instructions embedded in the analyzed source code before they are included in the documentation output.
Audit Metadata