ClawHub
Back to skill

Security audit

DaData.ru

Security checks for vulnerabilities and agentic risk

Overview

The DaData search workflow is coherent, but its automatic setup fallback executes unverified downloaded code and needs review.

Review and install the CLI separately using a verified release before allowing this skill to run. Check its automatic skill synchronization; the [command reference](https://github.com/oomol-lab/oo-cli/blob/main/docs/commands.md) documents OO_SKILLS_SYNC_DISABLED. Send only query information you intend OOMOL and DaData to receive. The bundled instructions were fully inspected, but external installer contents and hosted connector implementations remain unverified.

A.I.G

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

SkillSpector

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

Installing the documented connector CLI is a plausible prerequisite, not evidence of malicious scope expansion. However, the fallback instructs the agent to execute mutable remote installation scripts without integrity verification or explicit installation approval, creating a supply-chain code-execution risk beyond the advertised search/read operations; this is the same underlying issue as SC2.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
90% confidence
Finding

The supplied chunk performs a login operation rather than searching or reading DaData.ru data. Authentication could be a supporting implementation detail, but nothing in this chunk connects the oo CLI or its login operation to the declared DaData.ru functionality.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
99% confidence
Finding

The command pipes an unpinned HTTPS response directly into Bash; the PowerShell alternative similarly executes downloaded content with iex. A compromised distribution endpoint or malicious installer update could execute arbitrary code with the agent process's privileges and access local data or credentials; the missing-CLI condition reduces exposure frequency but does not make execution safe.

Content

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

The action workflow sends query data to a third-party service without a privacy warning.

Medium
Category
Output Handling
Confidence
91% confidence
Finding

The workflow instructs the agent to submit a JSON payload through the OOMOL connector to DaData.ru. For the listed address, email, and full-name suggestion actions, this can transmit personal information, but the skill provides no warning about that disclosure and labels untagged reads as safe to run directly.

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