Back to skill

Security audit

Twitter Image Generator

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward Twitter/X image-generation guide with no hidden execution, credential access, or unsafe persistence.

Before installing, be aware that the examples default to English and Twitter/X-specific dark-mode design assumptions. Adjust locale, wording, and style to your audience, and review any saved templates before reusing them.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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 (7)

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

The example generate_image call hard-codes locale: "en", which imposes a specific language/locale in the skill instructions. Because the file does not offer an opt-in or alternative locale choice, this is a natural-language policy concern under the language/locale rule.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

This example again specifies locale: "en", reinforcing an English-only default in the skill guidance. The file does not state that users may choose another language or that the constraint is justified for a region-specific use case.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
77% confidence
Finding

The file consistently frames design guidance specifically for Twitter/X, including platform-specific assumptions like dark-mode usage and mobile preview behavior. Under the policy category, this can be read as forcing a single platform context without any stated opt-in or alternative, which may limit user choice in a natural-language instruction file.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

This markdown file includes example calls with locale: "en", which presents English as the default output language without any note that users may choose another locale. Under the policy rule for natural-language violations, forcing a specific language without opt-in can be a locale policy issue.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

The thread header example sets locale: "en" with no accompanying explanation that this is only illustrative. Repeating a single mandatory locale across examples can imply that the skill requires English rather than offering language choice.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

This example explicitly specifies locale: "en" and does not document any region-specific or compliance reason for restricting output language. That can conflict with the requirement not to force a language or locale without user opt-in.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

The sample invocation uses locale: "en" as a fixed setting with no user-choice language guidance. Because the file is instructional markdown, this can be read as a default policy rather than an optional example.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.