runbook-generator

Pass

Audited by Gen Agent Trust Hub on Aug 28, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted data from a codebase (including configuration files, deployment scripts, and documentation) to generate a runbook. An adversary could include malicious instructions or deceptive content within these files to influence the agent's behavior or the resulting documentation.
  • Ingestion points: The workflow in SKILL.md and references/discovery-patterns.md directs the agent to scan the entire project structure and read various configuration and script files using Glob, Grep, and Read tools.
  • Boundary markers: The instructions lack specific boundary markers or requirements for the agent to distinguish between legitimate code/configuration and adversarial instructions embedded in comments or strings.
  • Capability inventory: The skill utilizes Read, Glob, Grep, Bash, Write, and Edit tools, allowing for substantial file system interaction based on analyzed content.
  • Sanitization: There are no requirements to sanitize or validate extracted commands or information before they are formatted into the final runbook.md file.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 28, 2026, 07:25 AM
Security Audit — agent-trust-hub — runbook-generator