Back to skill

Security audit

LifeImageRecognitionSkill

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple Chinese-language image helper that analyzes user-provided lifestyle photos and gives everyday advice, with no code execution, persistence, or hidden access.

Before installing, understand that the skill is written for Chinese-language use and asks you to upload photos for analysis. Avoid uploading images with faces of people who have not consented, addresses, documents, account information, or other private details.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (6)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The README is entirely written in Chinese and presents the skill as a Chinese-language assistant, but it does not state that language choice is optional or that the skill is specifically intended for a Chinese-only audience. This creates a natural-language locale policy concern because it implies a fixed language without explicit user opt-in or documented justification.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The file is a plain-text prompt, so SQP-3 applies. The entire instruction set is written to force a Chinese-language interaction, but there is no user opt-in, language selection mechanism, or documented region-specific justification, which matches the language/locale policy violation criteria.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill name, description, tags, input, and output text are all presented only in Chinese, with no indication that the skill supports other languages or that Chinese is a justified regional requirement. This can violate language or locale policy when a skill implicitly forces one language without user opt-in.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The natural-language content of the skill is presented only in Chinese, and there is no indication that users can choose another language or that the locale restriction is intentional and documented. The policy requires flagging skills that force a specific language without user opt-in.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

The skill explicitly asks users to upload lifestyle photos, which can contain faces, homes, locations, documents, or other sensitive personal details, yet the description provides no privacy warning or data-handling caution. In this context, the omission increases the chance that users share sensitive images without informed consent or awareness of privacy risks.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

This manifest describes the skill in very general terms: uploading any everyday-life image for recognition and advice. Because the description does not specify narrower trigger phrases, exclusions, or scope boundaries, it could overlap with many common image-analysis requests and make activation conditions ambiguous.

Content

No source excerpt is available for this finding.