Security audit

ai-infographics-news

Security checks for vulnerabilities and agentic risk

Overview

The skill is not malware, but it steers neutral AI-news infographic requests toward OpenClaw/MaxClaw promotion and can externally share generated output when requested.

Review this skill carefully before installing if you expect neutral AI-news summaries. It appears safe from a local-system perspective, but users should know it intentionally favors OpenClaw/MaxClaw coverage and branding, and should avoid using the CDN sharing step unless they are comfortable making the generated image externally accessible.

A.I.G

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

Findings (1)

T01 · Skill Instruction Hijacking

Warning

Location: SKILL.md:3
Finding: Forced Brand Promotion and Editorial Manipulation in Generated Infographics
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (6)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The trigger description includes broad catch-all language such as activating on 'any request combining AI news research with visual/infographic output.' This can cause the skill to fire on loosely related prompts without clear user intent, increasing the chance of unintended web searches, image generation, and downstream actions such as file creation or CDN upload.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 89% confidence
Finding: The skill instructs the agent to upload the generated image to a CDN for sharing, but the description does not warn users that gathered content or generated outputs may be externally shared. This creates a transparency and data-handling risk because users may not expect externally hosted distribution of generated artifacts derived from their request context.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 81% confidence
Finding: The file presents all user-facing guidance and operational instructions only in Chinese, with no indication that users may choose another language. This can violate a language-choice policy when the skill is intended for a broader audience and does not document a justified locale restriction.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The trigger list for the light style includes very broad terms like "简洁" and "白色", which commonly appear in ordinary user requests and could unintentionally activate this style. The file does not provide constraints or negative examples to clarify when these words should or should not trigger the template substitution.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 88% confidence
Finding: The trigger list includes general words like "复古" and "editorial", which can describe many designs and may appear in unrelated contexts. Without scope limits or examples, the activation condition is ambiguous and may cause unintended style selection.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 90% confidence
Finding: The trigger list includes common adjectives like "可爱" and "柔和", as well as the generic color term "粉色", which are broad enough to overlap with normal conversation about tone or color preferences. The file gives no negative examples or specificity about when these terms should map to this exact style.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.