Back to skill

Security audit

Instagram Image Generator

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward Instagram image-generation guide with no hidden code, local access, or unsafe persistence.

Safe to install for Instagram content generation. Review generated content before publishing, specify your preferred language if not English, and be careful with demographic targeting or confidential brand/customer information.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (10)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

This manifest-style description lists several specific triggers but then adds a very broad natural-language condition that could overlap with many ordinary requests about social media graphics. It does not provide boundaries or negative examples clarifying when the skill should not activate.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The natural-language examples hard-code locale: "en", which indicates the skill defaults output to a specific language/locale. The file does not state that the user can choose another locale or that English is required for a justified region-specific reason.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

This example repeats the English-only locale setting, reinforcing a default language policy that may override user preference. No nearby guidance explains that locale should be chosen based on the user's requested language or market.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The markdown examples set locale: "en", which instructs the skill toward a specific language/locale by default. The file does not indicate that English is optional, user-selectable, or required for a region-specific reason, so this appears to violate the language/locale policy.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

This example specifies locale: "en" directly in natural-language guidance. Because the file presents these as recommended templates and prompt examples, the hard-coded locale can steer usage toward English without giving users a language choice.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The example includes locale: "en" as a fixed parameter, which is a natural-language policy concern when no opt-in or alternative locale guidance is provided. There is no stated business or compliance reason for restricting output to English.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

This file repeatedly uses locale: "en" in its instructional examples, and this instance continues that pattern. Without an opt-in or documented rationale, the examples impose a specific locale contrary to the stated policy guidance.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The travel example sets locale: "en" directly, which is a language policy issue because the documentation does not offer localization choice or justify an English-only constraint. This can bias downstream usage toward English output.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The example hard-codes locale: "en" in instructional content, and the file gives no indication that users can select another language. That makes the locale restriction appear to be an undocumented policy violation rather than a justified constraint.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
78% confidence
Finding

This is a markdown file, so SQP-2 applies to omitted warnings about behaviors that could affect privacy or user data. The 'Niche Audience Profiles' section recommends targeting by age and gender lean, but the document does not include any caution about responsible audience segmentation or profiling considerations.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.