runbook-generator
Pass
Audited by Gen Agent Trust Hub on Apr 12, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious behaviors such as obfuscation, persistence, or data exfiltration were detected. The skill operates entirely on local files and references internal templates.\n- [COMMAND_EXECUTION]: The
scripts/runbook_generator.pyscript performs file system operations to create directories and write markdown files, which is necessary for its intended purpose as a documentation generator.\n- [PROMPT_INJECTION]: The generator script interpolates user-provided strings (service name, owner, and environment) directly into markdown templates. This creates an indirect prompt injection surface if the resulting documentation is later processed by an AI agent.\n - Ingestion points: The service, owner, and environment command-line arguments used in
scripts/runbook_generator.py.\n - Boundary markers: Absent; user inputs are directly formatted into the markdown content without delimiters.\n
- Capability inventory: The script has the capability to write text files to the local filesystem using standard library functions.\n
- Sanitization: None; the script performs no validation or escaping of the user-provided strings before interpolation.
Audit Metadata