Back to skill

Security audit

neon-object-storage

Security checks for vulnerabilities and agentic risk

Overview

The skill’s storage setup, credential handling, and file operations are disclosed and consistent with its stated purpose.

Confirm the target project and branch, inspect the configuration plan before deployment, keep credential files out of version control, and choose public-read buckets only for files intended for everyone. The advisory concerns were not substantiated by the complete artifact; the supplied static scan reported no findings.

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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
90% confidence
Finding

The supplied code performs a configuration deployment, with no visible bucket, object, upload, or database-branch storage operations. Configuration deployment could support storage setup, but no configuration or other context establishes that connection here. As supplied, the code's demonstrated purpose differs materially from the declared storage functionality.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
88% confidence
Finding

The supplied command concerns managing skills, not buckets, objects, presigned URLs, or storage branching. Although setup can support a declared capability, this chunk provides no evidence connecting that setup to the described storage service. The assessment is limited to the supplied command; any subsequently installed content is unknown.

Content

No source excerpt is available for this finding.

Credential Access

High
Category
Privilege Escalation
Confidence
60% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · SKILL.md (reported line 105)May include surrounding context.

When buckets is declared, Neon injects AWS-standard S3 env vars so the AWS SDKs work from the environment with zero extra config. Inside a deployed Neon Function these are injected automatically; locally, pull them onto disk (or inject them at runtime) via the CLI:

bash
neon env pull            # writes the branch's vars into .env (or .env.local)
# or, without writing a file, inject at runtime:
neon-env run -- <your dev command>

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 23)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