ticket-craft

Pass

Audited by Gen Agent Trust Hub on Apr 3, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill includes a /create-ticket workflow that directs the agent to read local project files to understand the current implementation and patterns. This creates an indirect prompt injection surface.
  • Ingestion points: Local source code, tests, and configuration files read during context detection.
  • Boundary markers: The skill does not define specific delimiters or instructions to protect the agent from malicious instructions embedded within the files.
  • Capability inventory: The skill is intended for high-capability agents that typically have shell and file-system access.
  • Sanitization: No content validation or sanitization process is specified for the ingested data.
  • [SAFE]: No patterns of obfuscation, unauthorized network operations, or hardcoded credentials were detected. The skill follows established software documentation standards.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 3, 2026, 06:31 AM