gentle-ai-cognitive-doc-design
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process documentation content which may come from untrusted sources in a repository.
- Ingestion points: Documentation files such as READMEs, contributor guides, architecture notes, and PR descriptions as seen in the 'When to Use' section.
- Boundary markers: No explicit delimiters or instructions to ignore embedded instructions are provided when processing this content.
- Capability inventory: The skill utilizes shell commands via
gitandgh. - Sanitization: No sanitization or content validation steps are described for the processed text.
- [COMMAND_EXECUTION]: The skill provides example shell commands to analyze the repository state.
- Evidence: The
git diff --name-only -- '*.md'command is used to list changed markdown files. - Evidence: The
gh pr view <PR_NUMBER> --json additions,deletions,changedFilescommand is used to inspect pull request metrics via the GitHub CLI.
Audit Metadata