Back to skill

Security audit

Pinecone

Security checks for vulnerabilities and agentic risk

Overview

The Pinecone workflow has clear safeguards, but its setup fallback executes unverified remote code without clear user approval.

Review and install the CLI separately before allowing this skill to run. Check its automatic skill-installation settings and use a narrowly scoped Pinecone connection. OOMOL is the disclosed intermediary for requests and API credentials. Keep the write/delete approval requirements; the remote installer and hosted connector implementations were not included in the artifact.

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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (5)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The supplied code executes an Oomol installation script rather than performing Pinecone operations. No connection between this installer and the declared Pinecone functionality is established, so it is not justified as a supporting implementation detail. The downloaded script's contents and any further effects are not visible in the supplied code.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
83% confidence
Finding

The supplied code only performs a CLI login, which is materially different from the declared Pinecone data-management purpose. Authentication could be a supporting implementation detail, but this chunk provides no evidence connecting the login to Pinecone.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

Piping a live HTTPS response directly into Bash executes remote code without a pinned version, independent integrity verification, or inspection. A compromised distribution endpoint or altered installer could execute arbitrary commands with the agent's permissions; HTTPS and the legitimate dependency context do not eliminate this supply-chain risk, and the PowerShell fallback has the same weakness.

Content

Scanner excerpt · SKILL.md (reported line 66)May include surrounding context.

Fallback setup executes downloaded installer scripts without warning the user about local system changes or requesting approval.

Medium
Category
Output Handling
Confidence
96% confidence
Finding

The missing-CLI fallback instructs the agent to execute a downloaded installer without a separate approval step or explanation of local changes. Although conditional on a setup failure, this expands a Pinecone task into local code execution with the agent process's permissions; the write-confirmation rules only explicitly cover Pinecone state changes.

Content

No source excerpt is available for this finding.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
80% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 87)May include surrounding context.

md
- **`OOMOL_INSUFFICIENT_CREDIT`** — OOMOL billing stop. Recharge at `https://console.oomol.com/billing/token-recharge` before retrying.

- **HTTP 402 without `OOMOL_INSUFFICIENT_CREDIT`** — the third-party account itself has no active plan or credit. Report the provider error message as is; do not ask the user to recharge OOMOL.

## Resources