Back to skill

Security audit

Auto Repair

Security checks for vulnerabilities and agentic risk

Overview

This is a simple nearby auto repair lookup skill with a low-risk packaging issue: it points to an absolute local response-format file outside the reviewed artifact.

Before installing, confirm the publisher fixes or accepts the non-portable absolute STANDARD_RESPONSE.md reference. The skill should only be used when you intend to share an authorized location for nearby auto repair search, and broad trigger wording may cause occasional over-invocation on general car repair questions.

Vulnerability Patterns
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
  • 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
Findings (1)

T05 · Unauthorized Access and Privilege Escalation

Note
Location
SKILL.md:21
Finding

Absolute Local File Reference Crosses the Packaged Skill Boundary

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The manifest description says to invoke the skill when the user asks for 'car repair near me,' which is a common natural-language phrase and does not define clear boundaries for when the skill should or should not activate. Without negative examples or tighter scope, this could cause unintended invocation on casual or ambiguous location-repair queries.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The trigger list includes broad terms such as 'car repair' and '汽车维修 附近' without clarifying required intent, context, or exclusions. Because these phrases can appear in ordinary conversation or in requests for repair advice rather than local business search, the activation condition is too vague.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
71% confidence
Finding

The skill documentation mixes Chinese and English terms such as 'Nearby Auto Repair,' 'Auto Repair,' and 'car repair' without stating whether the user can choose their preferred language or locale. This may amount to a language-policy issue if the skill behavior or presentation defaults to mixed-language output without user opt-in.

Content

No source excerpt is available for this finding.