Back to skill

Security audit

AI接单画师工作站

Security checks for vulnerabilities and agentic risk

Overview

The skill is a coherent AI image-order workflow, but it handles customer face photos and external delivery with unclear consent, retention, provider, and privilege boundaries.

Review carefully before installing. Use only in a restricted workspace, do not run the agent as administrator, require explicit customer consent before uploading face photos, restrict input image paths, and define approved image providers, cloud storage, link expiration, recipient checks, and deletion rules.

Vulnerability Patterns
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (2)

T05 · Unauthorized Access and Privilege Escalation

Warning
Location
SKILL.md:42
Finding

Overprivileged Command Execution Capability

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Error
Location
SKILL.md:98
Finding

Unspecified External Processing and Delivery of Sensitive Facial Images

Content
View full analysis
Remediation
View remediation
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 (4)

Missing User Warnings

High
Category
Not specified by scanner
Confidence
96% confidence
Finding

The workflow explicitly accepts customer selfies and routes them to external portrait-generation services, but it does not clearly warn users that their photos may be transmitted to third-party APIs. Because face images are highly sensitive biometric data, lack of informed consent and disclosure creates significant privacy, compliance, and trust risks.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill description uses very broad activation language such as applying whenever AI model calls, agent orchestration, or LLM applications are needed. This can cause the skill to be invoked outside its narrowly intended image-generation workflow, increasing the chance it handles unrelated sensitive data or triggers exec/network actions in inappropriate contexts.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The description states '支持中文交互' and presents the skill as Chinese-interaction oriented, but does not offer language selection or clarify that Chinese is optional. This can violate language/locale policy expectations when a skill appears to force a specific language without user opt-in.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill states that generated images are downloaded locally and later delivered via network disk links or messaging channels, but it does not clearly warn users about local storage, retention, or external sharing of both generated and user-provided images. This creates avoidable risk of unauthorized disclosure, over-retention, and mishandling of personal or commercial artwork assets.

Content

No source excerpt is available for this finding.