create-runbook

Pass

Audited by Gen Agent Trust Hub on Mar 5, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it incorporates untrusted user data from the 'topic' and 'service' arguments directly into generated markdown files and file paths.\n
  • Ingestion points: The 'topic' and 'service' arguments are sourced directly from user input during invocation.\n
  • Boundary markers: No delimiters or safety instructions are used to isolate user-provided data from the system's generation logic, allowing malicious input to potentially influence the output instructions.\n
  • Capability inventory: The skill utilizes the 'Write' tool to create files and the 'Read', 'Glob', and 'Grep' tools to scan the filesystem for existing runbooks.\n
  • Sanitization: There is no evidence of validation or sanitization for input strings before they are used in file path construction or content generation, which could facilitate path traversal attacks.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 5, 2026, 04:21 AM