Back to skill

Security audit

neon-postgres-egress-optimizer

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent Neon/Postgres cost-optimization guide, but users should review the optional infrastructure changes before applying them.

Install only if you want Neon/Postgres cost and egress optimization help. Before allowing an agent to run SQL resets, create extensions, install @neon/config, or run neon config apply, confirm the target database or Neon branch and review the resulting config; the optional ttl setting can expire future ephemeral branches.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (4)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The activation condition includes general code-review phrasing ('reviewing query patterns for cost efficiency') that is broader than the named purpose of Neon Postgres egress optimization. Overbroad routing can cause the skill to activate in contexts where it is not the best fit, increasing the chance it suggests unnecessary database or infrastructure changes during ordinary review tasks.

Content

No source excerpt is available for this finding.

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
80% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · SKILL.md (reported line 19)May include surrounding context.

FIRST: Use the parent neon skill for a Neon overview, getting started with Neon, Neon development best practices, and more.

If the neon skill is not installed, fetch it from https://neon.com/docs/ai/skills/neon/SKILL.md or install it with:

bash
neon skills -s neon -y

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill’s scope expands from diagnosing Postgres egress to recommending and applying broader Neon infrastructure cost controls in neon.ts. This increases the capability surface from analysis into environment configuration changes, which can cause unintended operational changes unrelated to the user’s original request and may be acted on with elevated trust because it appears in an optimization skill.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The documentation explicitly instructs applying infrastructure configuration changes (neon config apply) even though the skill is framed as an egress-optimization guide. In an agent context, actionable deployment commands can lead to unauthorized or accidental changes to Neon branches, broadening impact from advice to state-changing operations.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.