runbook-generator
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The
scripts/runbook_generator.pyscript incorporates user-supplied strings from command-line arguments directly into generated markdown files without sanitization. This creates a potential surface where malicious input could alter the instructions an agent follows when reading the generated runbooks. \n - Ingestion points: User-provided CLI arguments (
service,owner,environment) inscripts/runbook_generator.py. \n - Boundary markers: Absent; inputs are interpolated directly into markdown headers and code blocks. \n
- Capability inventory: The skill provides file-system writing capabilities through the script's
--outputparameter. \n - Sanitization: Absent; input is used directly in f-strings.
Audit Metadata