Prompt-injection style instruction pattern detected.
Warn
- Code
- suspicious.prompt_injection_instructions
- Location
- skills/queue-aiops/references/agent-guardrails.md:51
- Evidence
Copy this into your agent's system prompt:
Security audit
Queue AIops
Security checks for vulnerabilities and agentic risk
Overview
This plugin is a disclosed Redis/RabbitMQ operations tool with expected but potentially destructive admin actions that users should scope carefully.
Install only if you want an agent to operate Redis or RabbitMQ. Use read-only or tightly scoped broker credentials by default, and grant write permissions only when you are comfortable with actions such as Redis CONFIG SET, client kills, RabbitMQ policy changes, queue purges, and queue deletion; some message-destroying actions cannot be undone.
SkillSpector was not run because this plugin release contains no bundled skills.
Static analysis
Detected: suspicious.prompt_injection_instructions