Back to skill

Security audit

PractiTest

Security checks for vulnerabilities and agentic risk

Overview

PractiTest changes require approval, but automatic installation and undisclosed changes to local agent skills need review.

Review and install a verified CLI release separately before use. Account for its automatic changes to agent skills; the publisher documents OO_SKILLS_SYNC_DISABLED=1 to suppress startup synchronization. Use a narrowly scoped PractiTest connection and retain approval for every write or deletion. The remote installers and deployed connector were not verified. [CLI controls](https://github.com/oomol-lab/oo-cli/blob/main/docs/commands.md#environment-variables)

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
97% confidence
Finding

The supplied command runs an external installer rather than performing PractiTest operations. Nothing in the provided chunk establishes that this installer is a supporting dependency for PractiTest. The remote script's contents are unavailable, so its further behavior cannot be determined.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

Piping the HTTPS installer directly into bash executes whatever the remote endpoint returns without a pinned artifact or independent authenticity check. HTTPS protects transport but does not prevent a compromised publisher or distribution endpoint from delivering malicious code; this is the same underlying installation risk as SQP-2.

Content

Scanner excerpt · SKILL.md (reported line 61)May include surrounding context.

First-time setup executes remotely downloaded installation scripts without a security warning.

Medium
Category
Output Handling
Confidence
96% confidence
Finding

The setup instructions execute remotely retrieved shell or PowerShell code without prior inspection, integrity verification, or explicit installation approval. Although execution is conditional on a missing CLI, a compromised distribution endpoint could supply code that runs with the agent's local permissions and accesses files or credentials.

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 82)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