github-readme-maintenance
Pass
Audited by Gen Agent Trust Hub on Aug 14, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes standard shell commands such as
gitandsedto interact with local repositories. These commands are used to inspect the repository state, list files, and verify changes before finalization, which is appropriate for the skill's stated purpose of documentation maintenance. - [INDIRECT_PROMPT_INJECTION]: The skill processes external documentation files (e.g.,
README.md,AGENTS.md) which could contain malicious instructions designed to influence the agent's behavior during a maintenance task. - Ingestion points: The agent is instructed to read local files via
git show,git ls-tree, and standard file system access. - Boundary markers: The instructions do not specify formal delimiters for the ingested content, but they include strong directives to verify file and section context before performing any changes.
- Capability inventory: The skill has the capability to execute shell commands (
git) and modify repository contents. - Sanitization: The skill mitigates risks by requiring the agent to ground all guidance in accepted implementations, perform minimal edits, and strictly validate diffs before finalizing any publication.
Audit Metadata