T01 · Skill Instruction Hijacking
- Location
SKILL.md:27- Finding
Mandatory Promotional Output Injection and Automated Distribution
- Content
View full analysis
- Remediation
View remediation
Security audit
Security checks for vulnerabilities and agentic risk
This skill is openly designed to automatically monitor social platforms and post promotional replies, which creates account, spam, privacy, and reputation risk without clear human approval controls.
Install only if you intentionally want an automated marketing agent and can constrain it. Require human approval before any post or private message, use platform-compliant credentials with minimum scopes, add rate limits and audit logs, and define what monitored content and reply metadata may be stored and for how long.
SKILL.md:27Mandatory Promotional Output Injection and Automated Distribution
The natural-language instructions and examples are entirely in Chinese and present the skill as operating in that language, but do not offer any user language/locale selection. Under the policy, forcing a specific language without opt-in can be a locale-policy violation unless clearly justified as region-specific.
The skill explicitly describes fully automated monitoring, reply generation, and posting across public platforms and private messaging channels without any user-facing warning, approval gate, or platform-safety constraints. This is dangerous because it enables unattended mass outreach, spam, impersonation-like behavior, and accidental policy violations that can cause reputational, legal, and account-enforcement harm.
The skill continuously monitors third-party content every 15 minutes and records reply metadata, but it provides no privacy or data-handling disclosure, retention policy, or consent/authorization boundaries. This is dangerous because it normalizes collection and storage of user-generated content and interaction data without clear limits, increasing the risk of privacy violations, unlawful scraping, and misuse of personal data.