T01 · Skill Instruction Hijacking
- Location
SKILL.md:60- Finding
Downstream Moderation Avoidance Instruction
- Content
View full analysis
- Remediation
View remediation
Security audit
Security checks for vulnerabilities and agentic risk
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.
SKILL.md:60Downstream Moderation Avoidance Instruction
SKILL.md:118Forced Brand Promotion and External Traffic Redirection
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.
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.
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.