Security audit

Где бензин — АЗС России

Security checks for vulnerabilities and agentic risk

Overview

ClawScan marks this skill suspicious because its location-search workflow may send a user’s address or coordinates to gde-benzin.ru without clearly explaining that disclosure; no clear malicious behavior was reported.

Review the location-sharing concern before installing, especially if you might enter a precise address or coordinates. Skillspector scanned all six listed components, but marked analysis partial because a local reference in SKILL.md was missing; the overall verdict has medium confidence. A separate scanner reported no findings.

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

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access

Findings (5)

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.

Skill declares no tool scope ('permissions' or 'allowed-tools') but code capabilities were detected: network.

Medium

Category: MCP Least Privilege
Confidence: 70% confidence
Finding: Without declared permissions the skill's intent is opaque and cannot be validated.
Content: No source excerpt is available for this finding.

The location-search workflow lacks a warning that user location data is sent to a third-party service.

Medium

Category: Output Handling
Confidence: 90% confidence
Finding: The workflow permits user-provided or geolocation-derived coordinates without explicitly explaining that the search area is transmitted to gde-benzin.ru; address lookup likewise sends the entered place text. Naming the API provides some transparency, but permission to obtain location does not necessarily establish informed permission to disclose precise whereabouts to an external provider.
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.