Security audit

LinkedIn Image Generator

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed LinkedIn image-generation guide with no executable code, hidden behavior, credential handling, or persistence beyond optional template creation for design reuse.

Before installing, note that the skill may activate on broad LinkedIn-related requests and its examples default some image generations to English. Review generated visuals before posting, especially for brand accuracy, language, claims, and LinkedIn policy fit.

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

SkillSpector

Vulnerability Patterns

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
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (6)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The skill description includes broad triggers such as 'LinkedIn', 'professional post', and general requests to create visual content for LinkedIn, which can cause the agent to invoke this skill for loosely related or ambiguous prompts. Over-broad routing can lead to inappropriate tool activation, unintended file/reference access, or generation behavior outside the user's actual intent, especially in multi-skill environments where precise dispatch matters.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The example sets locale: "en", which imposes a specific language/locale in the skill instructions. The file does not state that English is optional or that the locale should be selected based on user preference, so this can conflict with language-choice policy expectations.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The example explicitly sets locale: "en", which imposes a specific language/locale in natural-language guidance. The file does not indicate that other locales are supported or that English is only an example, so this can conflict with a policy requiring user language choice or opt-in.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 91% confidence
Finding: This example sets locale: "en" directly, prescribing a language choice without documenting user opt-in or alternatives. In instructional content, repeated hard-coded locale values can signal a language policy issue.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The file includes another hard-coded locale: "en" value in example content, with no accompanying note that the user may choose another language. That creates a natural-language locale constraint not justified in the document.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 91% confidence
Finding: This line hard-codes English as the locale in a user-facing example. Because the document does not offer language choice or explain a region-specific requirement, it may violate language/locale policy expectations.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.