Back to skill

Security audit

Morfeo Content Pipeline

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly a disclosed Morfeo Labs video-generation workflow, but it explicitly tells agents to work around Gemini moderation by switching languages.

Install only if you intend to run a Morfeo Labs marketing pipeline and are comfortable with scheduled draft creation through external media services. Remove or revise the language-switching moderation workaround before use; moderation blocks should be handled by making prompts compliant, not by bypassing provider safeguards.

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 (2)

T01 · Skill Instruction Hijacking

Error
Location
SKILL.md:60
Finding

Downstream Moderation Avoidance Instruction

Content
View full analysis
Remediation
View remediation

T01 · Skill Instruction Hijacking

Error
Location
SKILL.md:118
Finding

Forced Brand Promotion and External Traffic Redirection

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (3)

Ssd 2

High
Category
Not specified by scanner
Confidence
99% confidence
Finding

The skill explicitly instructs operators to write the brief in English to avoid Gemini moderation filters in Spanish. Deliberately reformulating prompts to evade safety controls undermines model safeguards and increases the chance of generating disallowed, deceptive, or policy-violating content.

Content

No source excerpt is available for this finding.

Ssd 2

High
Category
Not specified by scanner
Confidence
99% confidence
Finding

The troubleshooting guidance again recommends switching languages when moderation is triggered, which operationalizes safety-evasion as part of the workflow. Embedding this as a known solution normalizes bypass behavior and makes abuse easier and more repeatable in production.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The instructions require 'Español argentino coloquial auténtico' and prescribe specific regional slang while rejecting alternatives. This is a natural-language locale policy constraint applied unconditionally, and the file does not present it as an opt-in choice or clearly justify it as a region-specific compliance or localization requirement.

Content

No source excerpt is available for this finding.