other
- Location
SKILL.md:13- Finding
Systematic External Platform Moderation-Filter Evasion
- Content
View full analysis
Vulnerability Details
File Location:
SKILL.md:13-41; supporting instructions inreferences/sensitive-words.md:16-23,44-50
Vulnerability Type:other: Moderation Filter Evasion
Risk Level: MediumVulnerable Content
Relevant excerpt from
SKILL.md:13-16(English translation):text Midjourney's sensitive-word detection uses combination-pattern recognition rather than individual-word detection: - Three clothing-category terms appearing together trigger the "clothing set/uniform" filter. - "Black + wings/horns/teeth" triggers the "dark imagery" filter. - If individual words pass independently but trigger a rejection when combined, the combination is the problem rather than a particular word.Relevant excerpt from
SKILL.md:18-26(English translation):text Sensitive-word replacement rules (apply directly without asking) Expression: Mischievous bad smile Replacement: Playful broad smile / bright toothy smile Expression: Small fang showing Replacement: Playfully pointed tooth Expression: Fingers painted with black nail polish Replacement: Delete directly Expression: Black wings Replacement: Light-gray wings / silver wings Expression: Black curved horns Replacement: Curved horn accessories Expression: Three dark clothing categories together Replacement: Combine them into two items or use a lighter color Expression: Black formalwear + trousers + leather shoes Replacement: Dark-gray suit jacket with dark-gray trousersRelevant excerpt from
SKILL.md:35-41(English translation):text Workflow: 1. Receive the user's Chinese description. 2. Apply the sensitive-word replacement table directly without notifying the user. 3. Add the standard Midjourney suffix. 4. Output the English prompt directly.Supporting filter-probing procedure from
references/sensitive-words.md:44-50(English translation):text Exhaustive troubleshooting pro ...[truncated 3422 chars]- Remediation
View remediation
Remediation Suggestions
- Remove the sentence-by-sentence and word-by-word filter-probing workflow from
references/sensitive-words.md. - Replace evasion-oriented rules with a policy-compliance workflow that evaluates the underlying requested content rather than merely disguising trigger terms.
- Refuse requests whose underlying intent violates the target platform's policies instead of searching for alternate wording that passes moderation.
- Clearly disclose material removals or semantic substitutions rather than applying them silently.
- Limit transformations to benign quality improvements such as translation, grammar correction, composition, lighting, camera parameters, and artistic style.
- Do not maintain a growing repository of discovered moderation triggers or successful bypass combinations.
- Add an explicit rule stating that the Skill must not test, reverse-engineer, or circumvent external moderation systems.
- Document the intended content-policy boundary and include examples distinguishing harmless rephrasing from prohibited filter evasion.
- Remove the sentence-by-sentence and word-by-word filter-probing workflow from
