Back to skill

Security audit

Text-to-Comic · 文字转漫画

Security checks for vulnerabilities and agentic risk

Overview

ClawScan rates this skill benign because the reported findings are not considered purpose-related risks, while noting that one bundled image was not fully inspected and the overall evidence is incomplete.

The verdict is benign with medium confidence, but the scan is incomplete: 23 of 24 components were scanned, and static analysis was degraded for the uninspected image. Consider whether the language constraints suit you and review the skill’s tool access in your host before installing.

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
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • 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 (5)

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 136)May include surrounding context.

md
- `characters/protagonist-ref.png` is an optional reference sheet; use it only when the host image tool accepts reference images, otherwise rely on the text anc

Hard constraints prescribe English image text and Chinese captions without offering a user language choice.

Medium
Category
Output Handling
Confidence
96% confidence
Finding

The language-separation and typography constraints prescribe English text within images and Chinese captions and narration without conditioning these choices on the user's requested language. Generation reliability explains the English-image-text preference, but does not justify requiring Chinese captions for users of other languages; the same constraints appear at lines 151–153.

Content

No source excerpt is available for this finding.

Skill declares no tool scope ('permissions' or 'allowed-tools') but code capabilities were detected: file_read, file_write.

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.

The workflow prescribes Chinese captions and narration without first establishing the user's preferred output language.

Medium
Category
Output Handling
Confidence
94% confidence
Finding

The language-separation instructions prefer Chinese for captions, narration, and overlays regardless of the user's language; L211 also instructs adding Chinese captions during assembly. Although English in-image text has a stated rendering-quality rationale, the Chinese caption requirement has no equivalent justification or user opt-in, and allowing all-Chinese bubbles does not offer a general language choice.

Content

No source excerpt is available for this finding.

The template requires English phrases in `must_keep` without language choice or a documented justification.

Low
Category
Output Handling
Confidence
98% confidence
Finding

The instruction “must_keep 用英文短语写” explicitly requires the must_keep field to be written in English. No user opt-in or technical justification for this language restriction is provided.

Content

No source excerpt is available for this finding.