Back to skill

Security audit

Yacli Yandex

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Yandex Mail, Disk, and Calendar integration that uses an existing yacli MCP setup and includes appropriate confirmation rules for sensitive actions.

Install this only if you intend to let OpenClaw operate a configured Yandex account through yacli. Verify the upstream yacli installation yourself, keep real tokens and account snapshots out of the skill bundle, and review confirmations carefully before allowing email sends, public file links, uploads/downloads, or calendar changes.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (7)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The manifest description includes only Russian text for the functional description, which can impose a specific language/locale expectation at activation time. The file later includes both English and Russian sections, but the top-level description shown to routing or users does not offer a language choice or indicate opt-in.

Content

No source excerpt is available for this finding.

Ae4

Medium
Category
analysis-evasion
Confidence
80% confidence
Finding

Suspicious Unicode normalization or mixed-script content

Content

No source excerpt is available for this finding.

Ae4

Medium
Category
analysis-evasion
Confidence
80% confidence
Finding

Suspicious Unicode normalization or mixed-script content

Content

No source excerpt is available for this finding.

Ae4

Medium
Category
analysis-evasion
Confidence
80% confidence
Finding

Suspicious Unicode normalization or mixed-script content

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The document explicitly presents fixed English and Russian sections, indicating a language constraint rather than offering the user a choice of preferred language or locale. Under the policy, forcing specific languages without opt-in is a natural-language policy concern.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
78% confidence
Finding

The document is split into fixed English and Russian sections, which imposes specific language choices in the skill documentation without explicitly offering a user-selected language preference. This can conflict with a language/locale policy requiring opt-in or choice rather than assuming supported languages.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

The script explicitly emits bilingual English and Russian output, but it does not indicate that language selection is optional or configurable. Under the policy, forcing a specific language or locale without user opt-in can be a natural-language policy issue unless the constraint is documented and justified.

Content

No source excerpt is available for this finding.