Back to skill

Security audit

Placid

Security checks for vulnerabilities and agentic risk

Overview

The Placid workflow is coherent, but its setup instructions can lead an agent to run unchecked internet code without first asking for approval.

Review the setup behavior before installing. Install a verified, fixed CLI release separately and require approval before any downloaded installer runs. Understand that OOMOL handles the connected Placid account and action payloads. Keep the skill's write and deletion confirmations enabled. No malicious behavior was established, but the external installer contents remain unverified.

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
98% confidence
Finding

The declared purpose concerns Placid data operations, but the supplied chunk executes an Oomol installer. Nothing in the chunk establishes this installer as a supporting dependency for Placid. The remote script's contents and any further effects are not available for inspection.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
82% confidence
Finding

Authentication can be a legitimate supporting step, but the supplied chunk consists solely of an oo login command and provides no connection to Placid. Its demonstrated purpose therefore differs from the declared purpose. The command alone does not establish credential theft or other malicious behavior.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

The command pipes a mutable remote script directly into Bash without pinning a version or independently verifying integrity. Although the domain is relevant to the documented CLI and HTTPS protects transport, a compromised distribution endpoint or malicious script update could execute arbitrary commands with the agent's permissions; the PowerShell alternative has the same underlying risk.

Content

Scanner excerpt · SKILL.md (reported line 59)May include surrounding context.

The setup workflow executes downloaded installer scripts without warning the user about remote code execution and local system changes.

Medium
Category
Output Handling
Confidence
94% confidence
Finding

When the CLI is missing, the skill directs installation using remotely downloaded scripts without explicitly requiring user approval for code execution or local system changes. The conditional setup makes execution less frequent but can still turn a Placid request into execution of unreviewed code with the agent process's local permissions.

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 80)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