T08 · Insecure Dependencies
Warning
- Location
SKILL.md:17- Finding
Unpinned Global Installation of Privileged Third-Party CLI Packages
- Content
View full analysis
- Remediation
View remediation
Security audit
China IM Workflow CLI
Security checks for vulnerabilities and agentic risk
Overview
This skill is a disclosed workflow guide for using Feishu, DingTalk, and WeCom CLIs, with install and authentication risks users should handle carefully.
Install only the CLIs you need, verify package provenance, prefer pinned or project-local installs, grant minimal platform scopes, use previews before sending messages, and review commands carefully before allowing the agent to post, create, update, or delete enterprise content.
Vulnerability Patterns
- Insecure DependenciesIntroduces malicious components through unsafe dependency sources
- 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
Findings (1)
Vulnerability Patterns
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
- Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
- Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 88% confidence
- Finding
The skill metadata and body are centered on Chinese-language triggers and Chinese enterprise IM workflows, and the opening instruction positions the agent as an expert in China's platforms without offering any language or locale choice. This can violate language/locale policy when a skill constrains interaction to a specific language or region by default rather than documenting it as an opt-in or region-specific limitation.
- Content