Back to skill

Security audit

Picture Edit

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward local image-editing helper with no evidence of hidden network access, persistence, credential use, or destructive behavior.

Reasonable to install for local image editing. Use it with images you trust when possible, consider pinning Pillow to a reviewed version, and expect the documentation and examples to be Chinese-first.

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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • 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
Findings (6)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The README content is written entirely in Chinese, including the skill overview, API documentation, and usage guidance, with no indication that users can choose another language. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill is explicitly centered on the colloquial trigger phrase “P一下图片,” which is broad, conversational, and likely to appear in normal user requests unrelated to intentional invocation boundaries. This can cause accidental activation or routing collisions with other skills, leading to unintended tool use, surprising behavior, or interception of image-editing requests that should remain under general assistant control.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The module docstring and subsequent printed status messages indicate the skill is presented in Chinese only. Under the policy, forcing a specific language without user opt-in or a documented region-specific justification is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
86% confidence
Finding

The entire skill description and API documentation are written only in Chinese, with no indication that other languages are supported or that the user can choose a preferred language. Under the stated policy, language constraints should either be optional for the user or clearly justified as region-specific.

Content

No source excerpt is available for this finding.

Unpinned Dependencies

Low
Category
Supply Chain
Confidence
96% confidence
Finding

The dependency is specified as pillow>=10.0.0, which allows installation of any future Pillow release and prevents reproducible builds. This weakens supply-chain control because different environments may resolve to different versions, including versions later found vulnerable or behaviorally incompatible.

Content

Scanner excerpt · requirements.txt (reported line 1)May include surrounding context.

text
pillow>=10.0.0

Unverifiable Dependency: pillow has 16 known advisory(ies) (CVE-2016-2533 (Pillow buffer overflow in ImagingPcdDecode); CVE-2023-50447 (Arbitrary Code Execution in Pillow); CVE-2021-27922 (Pillow Uncontrolled Resource Consumption) +13 more), but the manifest does not pin a version, so it is unknown whether the installed release is affected

Low
Category
Supply Chain
Confidence
90% confidence
Finding

Pillow has a history of multiple security advisories, and because the manifest does not pin an exact version, it is not possible to verify whether the resolved installation is affected. In a skill that may process untrusted images, this uncertainty increases risk of exposure to known flaws such as denial of service or, in some versions, more severe memory corruption or code execution issues.

Content

No source excerpt is available for this finding.