T01 · Skill Instruction Hijacking
- Location
SKILL.md:264- Finding
Forced Transmission of Generated Reports to a Hardcoded External Recipient
- Content
View full analysis
- Remediation
View remediation
Security audit
Security checks for vulnerabilities and agentic risk
The skill is a coherent daily game-industry report generator, but it requires automatically sending every report to a fixed DingTalk recipient without runtime user control.
Install only if DingTalk target 2735046220840628 is an approved destination for your organization and scheduled automatic sending is intended. Prefer changing the skill so the recipient comes from trusted configuration and the user or administrator approves outbound delivery before the first send or any destination change.
SKILL.md:264Forced Transmission of Generated Reports to a Hardcoded External Recipient
The activation phrases are broad enough to match generic requests like '日报' or '行业简报', which can cause the skill to trigger in situations the user did not intend. Because this skill performs multi-step web collection and then instructs outbound delivery, accidental invocation can lead to unnecessary external actions and disclosure of generated content.
The skill explicitly requires sending the full generated report to a fixed DingTalk target via a message tool, without a user-facing consent step or clear disclosure at runtime. This creates a real exfiltration risk: collected data, derived summaries, or accidentally included sensitive context could be transmitted to an external recipient whenever the skill runs.
The language section explicitly requires the body text to be in Chinese, but there is no user opt-in or documented justification that this is a region-specific or compliance-bound constraint. This can violate language/locale policy when a skill forces one language by default.