docset-updater
Pass
Audited by Gen Agent Trust Hub on Jul 30, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill manages documentation workflows by reading and updating standard repository files such as README.md, AGENTS.md, and various Markdown files in the docs/ directory. This behavior is consistent with its stated purpose.
- [COMMAND_EXECUTION]: The skill orchestrates complex documentation tasks through sub-agent delegation. This execution is limited to internal agent-to-agent task management for processing text and generating documentation content.
- [EXTERNAL_DOWNLOADS]: While the skill description mentions that a sub-skill (see-also-docs) performs network-bound discovery for gathering repository metadata, this skill itself does not initiate unverified downloads or execute remote scripts.
- [PROMPT_INJECTION]: The skill ingests configuration and style rules from repository files (AGENTS.md, REPO_STYLE.md). This represents a surface for indirect prompt injection, but the skill's capabilities are restricted to documentation generation, resulting in no identifiable risk.
Audit Metadata