Security audit
Postgres AIops
Security checks for vulnerabilities and agentic risk
Overview
The package’s database access and maintenance tools fit its stated purpose, with powerful write access clearly disclosed.
Start with a dedicated monitoring role and verified TLS. Require explicit agent approval before enabling live writes: MCP auditing does not enforce approval, and some operations cannot be undone. Protect credentials and audit files containing query text. SkillSpector did not assess the bundled skill; this review inspected its instructions, but not the separately downloaded runtime.
SkillSpector was not run because this plugin release contains no bundled skills.
Static analysis
No suspicious patterns detected.