Back to skill

Security audit

FLUX 图片生成替代|AI 图片生成与编辑

Security checks for vulnerabilities and agentic risk

Overview

This image-generation skill mostly matches its purpose, but it needs review because it sends user images and downloads results using server-provided URLs without validating those destinations.

Install only if you are comfortable sending prompts and selected reference images to AI Hive and relying on AI Hive-provided storage/result URLs. Prefer a virtual environment, a dedicated limited API key, and non-sensitive reference images until the package pins dependencies and validates upload/download destinations.

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:53
Finding

Unpinned Third-Party Dependency Installation

Content
View full analysis
Remediation
View remediation
``` 2. Pin all transitive dependencies and record cryptographic hashes. 3. Install with hash verification, for example: ```bash python3 -m pip install --require-hashes -r requirements.txt ``` 4. Document the expected trusted Python package index and avoid silently inheriting untrusted global or user-level index configuration. 5. Use a dedicated virtual environment with ordinary user privileges. 6. Add automated dependency vulnerability and integrity scanning to the release process. 7. Update `SKILL.md` and the import error message so they point to the reviewed requirements file rather than recommending an unconstrained installation. ]]>

T09 · Insecure Skill Coding Practices

Warning
Location
scripts/imagegen.py:231
Finding

Unvalidated Server-Provided Upload and Download Destinations

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 (3)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
94% confidence
Finding

The skill exposes executable shell commands, file access, environment access, and network behavior but does not declare any explicit tool scope or permission boundaries. In a skill that installs dependencies and invokes Python scripts making authenticated network requests, this omission increases the risk of over-privileged execution, unintended file/env access, or abuse if the skill or its scripts are modified or invoked with adversarial inputs.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The activation text is very broad and overlaps with generic image-generation and editing requests, which can cause the skill to trigger in many unrelated contexts. Because the skill is opinionated and forces a specific model/provider workflow, overbroad routing can redirect user tasks unexpectedly, leading to inappropriate tool use, unnecessary network transfer of images/prompts, and reduced user control over where sensitive media is sent.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The module docstring and all user-facing CLI guidance are written in Chinese, and the skill does not indicate any user choice of language or locale. Per the policy, forcing a specific language without opt-in is a natural-language policy violation unless the locale constraint is clearly documented and justified.

Content

No source excerpt is available for this finding.