Prompt-injection style instruction pattern detected.
Warn
- Code
- suspicious.prompt_injection_instructions
- Location
- skills/compliance-aiops/references/agent-guardrails.md:45
- Evidence
Copy this into your agent's system prompt:
Security audit
Compliance AIops
Security checks for vulnerabilities and agentic risk
Overview
This plugin is a disclosed offline compliance-evidence tool that reads local AIops audit logs and writes local evidence bundles, with no artifact-backed sign of hidden or unrelated behavior.
Install this only where the account is allowed to read the local AIops audit databases, because those logs may reveal sensitive operational history and approval details. Review the pinned uvx package source/provenance if your environment requires supply-chain assurance, and treat generated bundles as evidence artifacts rather than compliance certification.
SkillSpector was not run because this plugin release contains no bundled skills.
Static analysis
Detected: suspicious.prompt_injection_instructions