doc-maintenance
Pass
Audited by Gen Agent Trust Hub on May 15, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill contains diagnostic shell commands used for file management and project structure validation. Evidence includes the use of standard Unix utilities like find, ls, wc, and xargs to count Markdown files, list directory contents, and identify duplicate or empty files within the project. These tools are used for read-only diagnosis and local file organization.
- [PROMPT_INJECTION]: The skill describes a workflow that processes untrusted local data, which represents a surface for indirect prompt injection.
- Ingestion points: The agent is instructed to scan and classify the content of local Markdown files throughout the project directory.
- Boundary markers: No explicit delimiters or instructions to ignore embedded prompts within the processed documentation are present.
- Capability inventory: The skill enables the agent to move files between directories and modify the contents of index files such as CLAUDE.md.
- Sanitization: The instructions do not specify any validation or sanitization of the documentation content before it is read or acted upon.
Audit Metadata