Back to skill

Security audit

Peec AI

Security checks for vulnerabilities and agentic risk

Overview

The Peec reporting functions fit their purpose, but automatic setup can execute unverified software and introduce broader agent changes without clear user approval.

Review the setup behavior before installing. Prefer a verified CLI release installed under your control, and review its automatic skill synchronization. Peec access is routed through OOMOL, so authorize only the account access you need. The remote installer payloads and hosted connector implementation 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 (4)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The supplied command performs remote installer execution, not Peec AI data access. Nothing in the supplied chunk establishes that installing Oomol is a supporting requirement for the declared purpose. The downloaded script's contents and any subsequent effects are not visible.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
97% confidence
Finding

Piping a live remote script directly into Bash executes whatever the endpoint returns with the agent's local privileges, without an independent integrity check or review. Although the domain belongs to the stated integration provider and execution is conditional on a missing CLI, compromise of the distribution endpoint could expose local files and credentials or enable arbitrary system changes; the PowerShell alternative has the same weakness.

Content

Scanner excerpt · SKILL.md (reported line 58)May include surrounding context.

The fallback setup executes downloaded installation scripts without warning about local system changes.

Medium
Category
Output Handling
Confidence
91% confidence
Finding

The fallback directs the agent to install software after a missing-command error without first explaining local changes or obtaining explicit approval. This expands a read-only data request into local code execution and system modification; restricting installation to a genuine setup failure reduces frequency but does not supply authorization.

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 79)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