quasar-queue
Warn
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: MEDIUMPROMPT_INJECTION
Full Analysis
- [Prompt Injection] (SAFE): No direct override markers, jailbreak attempts, or system prompt extraction patterns were found.
- [Indirect Prompt Injection] (MEDIUM): The skill is vulnerable to indirect injection as it processes untrusted data (job payloads) to influence its output and actions.
- Ingestion points: The skill ingests 'payload required for the job' and user-provided 'queue configuration' parameters in SKILL.md.
- Boundary markers: Absent. No delimiters or 'ignore' instructions are used to wrap external content.
- Capability inventory: The skill is capable of job scheduling, queue configuration, and monitoring setup (BullMQ/BeeQueue/Redis operations).
- Sanitization: No input validation or sanitization mechanisms are defined in the instructions.
- [External Downloads] (SAFE): Mentions standard libraries like BullMQ and BeeQueue, but does not execute unverified remote code or download scripts from untrusted sources.
- [Data Exposure & Exfiltration] (SAFE): No access to sensitive files or unauthorized network communication patterns were identified.
Audit Metadata