Back to skill

Security audit

photo-three-principles

Security checks for vulnerabilities and agentic risk

Overview

This is a photography guidance skill with no executable code, persistence, credential use, or hidden side effects.

Installers should expect a Chinese-first photography education skill. It appears safe from a security perspective, but users who want multilingual responses may need clearer locale guidance from the publisher.

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
  • 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 (2)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
84% confidence
Finding

All prompts, expected behaviors, and notes are written exclusively in Chinese, and there is no indication that the skill supports user language choice or that it is intentionally limited to a Chinese-only audience. Under the policy rule, forcing a specific language without opt-in can be a natural-language policy violation.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
79% confidence
Finding

This JSON test file is a manifest-style file, so SQP-1 applies. The should-trigger case uses a broad question about 'basic principles' and 'how to judge whether a photo is good' without clearly defining the full trigger boundary, which can overlap with many general photography-help requests; although there are some negative examples, the activation scope still remains somewhat underspecified.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.