Back to skill

Security audit

营销图片

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly coherent for generating marketing images, but it needs review because its image upload path can send disguised or symlinked local files to an external service.

Review before installing if the agent may handle private local files. Only pass known real image files from trusted locations, avoid symlinked paths, understand that prompts and reference images go to AI Hive, and prefer installing dependencies in an isolated environment with pinned versions.

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)

T09 · Insecure Skill Coding Practices

Warning
Location
scripts/imagegen.py:209
Finding

Extension-Only Validation Allows Non-Image Files to Be Uploaded

Content
View full analysis
Remediation
View remediation

T08 · Insecure Dependencies

Note
Location
SKILL.md:59
Finding

Unpinned Runtime Dependency Installation

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (4)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
92% confidence
Finding

The skill invokes a Python script that can read and write files, use the shell, access environment variables, and make network requests, but the skill metadata does not declare any explicit tool or permission scope. This creates an overbroad execution surface where an agent may grant or assume capabilities beyond what is minimally required, increasing the risk of unintended file access, secret exposure, or network misuse if the script or inputs are later modified or abused.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The invocation text is very broad and overlaps with many generic marketing and design requests, which can cause the skill to trigger in situations the user did not specifically intend. While not a code-execution flaw by itself, overbroad routing can expose users to unnecessary file, network, or shell-capable behavior from this skill more often than needed, raising the chance of misuse or accidental data handling.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The module docstring and all user-facing guidance are written only in Chinese, and the CLI prompts/messages throughout the file assume Chinese-language interaction. Under the policy, forcing a specific language without opt-in is a natural-language policy violation unless the locale restriction is explicitly justified or optionality is offered.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
79% confidence
Finding

The file content is written primarily in Chinese, including the title and operational instructions, but does not state that the user may choose another language or that the locale is region-specific. Under the stated policy, a fixed language without opt-in can be a natural-language policy violation.

Content

No source excerpt is available for this finding.