Back to skill

Security audit

TypeSafe AI

Security checks for vulnerabilities and agentic risk

Overview

The TypeSafe AI workflow is plausible, but its setup can execute unverified software and introduce persistent agent skills without explaining those changes.

Review and verify the CLI before allowing installation. Its current upstream behavior includes persistent installation of other agent skills; disable startup synchronization with OO_SKILLS_SYNC_DISABLED=1 if those changes are unwanted, as documented in the linked CLI reference. Submit only content you intend OOMOL and TypeSafe AI to process. The bundled instructions were fully inspected, but the remote installers and installed release were not verified.

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 rather than TypeSafe AI data access. Nothing in the provided chunk establishes that this installation is a supporting dependency for the declared purpose. The installer’s contents and downstream effects are not supplied, so those cannot be assessed.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

The setup instructions pipe a mutable remote installer directly into Bash, allowing downloaded code to execute with the agent process's permissions without prior inspection or artifact verification; the PowerShell alternative has the same issue. Although installation is conditional on a missing CLI, a compromised distribution endpoint or installer could execute arbitrary commands and access local files or credentials.

Content

Scanner excerpt · SKILL.md (reported line 56)May include surrounding context.

The action workflow lacks a privacy warning for text or JSON submitted for evaluation.

Medium
Category
Output Handling
Confidence
88% confidence
Finding

The workflow instructs the agent to run connector actions, including evaluate, which submits text or structured JSON to TypeSafe AI through OOMOL. Although the connector is identified, the skill does not warn about sending potentially sensitive user content to external services, and its blanket statement that untagged actions are safe reads overlooks this privacy impact.

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 77)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