Security audit

舞台服装设计板

Security checks for vulnerabilities and agentic risk

Overview

This skill coherently generates local costume design board PNG/PDF files, with ordinary dependency and filename-safety caveats but no evidence of hidden, destructive, or data-exfiltrating behavior.

Install only in an isolated Python environment if possible, pin Pillow for reproducibility, and use simple character/version values without slashes, `..`, drive prefixes, or absolute paths. Review output paths before running if inputs may come from someone else.

A.I.G

Vulnerability Patterns

Insecure DependenciesIntroduces malicious components through unsafe dependency sources
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)

T08 · Insecure Dependencies

Warning

Location: SKILL.md:9
Finding: Unpinned Third-Party Dependency Installation
Content: View full analysis
Remediation: View remediation
``` 2. Generate and verify cryptographic hashes, then install with: ```bash python -m pip install --require-hashes -r requirements.txt ``` 3. Explicitly use a trusted package index rather than inheriting an uncontrolled mirror or environment configuration. 4. Retain the lockfile and hashes in the Skill package so the installed artifact is reproducible. 5. Periodically review and update the pinned version for security fixes. 6. Install dependencies in an isolated virtual environment or container under a non-privileged account. ]]>

T09 · Insecure Skill Coding Practices

Warning

Location: scripts/build_design_board.py:287
Finding: Output Directory Escape Through Unsanitized Filename Components
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
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)

Undeclared Tool Scope

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.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 88% confidence
Finding: The skill uses a Chinese display name and Chinese-only description/instructions, which indicates a fixed language/locale experience. The file does not offer an opt-in choice of language or explain that the skill is intentionally limited to a Chinese-speaking or region-specific context.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 83% confidence
Finding: SQP-3 applies to all file types and includes language or locale policy violations. This specification consistently uses Chinese text and Chinese-specific font choices, with no indication that users can opt into another language or that the locale restriction is documented as a justified regional requirement.
Content: No source excerpt is available for this finding.