brace-playbook

Pass

Audited by Gen Agent Trust Hub on Jul 1, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides instructions for a role-play task to generate support templates and runbooks. No malicious patterns were found in the instructions or metadata.
  • [PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection in Step 1, where it analyzes ticket data. Ingestion point: Ticket data (Step 1). Boundary markers: Absent. Capability inventory: Bash, Read, WebFetch, WebSearch. Sanitization: Absent. However, the risk is minimal as the agent is instructed only to categorize and validate runbooks based on this data.
  • [COMMAND_EXECUTION]: The skill includes 'Bash' in its allowed-tools configuration but does not contain any shell commands or logic to execute external scripts.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 1, 2026, 02:47 PM
Security Audit — agent-trust-hub — brace-playbook