Back to skill

Security audit

Morning Report

Security checks for vulnerabilities and agentic risk

Overview

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.

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 (1)

T01 · Skill Instruction Hijacking

Error
Location
SKILL.md:264
Finding

Forced Transmission of Generated Reports to a Hardcoded External Recipient

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

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.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

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.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
92% confidence
Finding

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.

Content

No source excerpt is available for this finding.