T08 · Insecure Dependencies
Warning
- Location
SKILL.md:105- Finding
Unpinned Third-Party Packages and Runtime Browser Download
- Content
View full analysis
- Remediation
View remediation
Security audit
wechat daily report
Security checks for vulnerabilities and agentic risk
Overview
The skill is mostly aligned with generating WeChat chat reports, but it handles full private group chat text without privacy safeguards and has misleading localized metadata.
Review this skill before installing. Only use it on WeChat chat logs you are authorized to process, redact sensitive names or messages first, run it in an isolated environment, and verify the missing scripts and prompt source before following the install or execution commands.
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
- MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
- 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
Findings (9)
Missing User Warnings
Medium
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The skill explicitly instructs users to extract full WeChat group chat text into
simplified_chat.txtand then feed it, together with stats, into an AI workflow, but it provides no warning, minimization guidance, consent requirement, or redaction step for personal or sensitive content. Because group chats commonly contain personal data, opinions, identifiers, and confidential discussions, this creates a real privacy exposure risk and may cause unauthorized disclosure to downstream tools or model providers.- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The file description is entirely in Chinese and describes a WeChat chat-record daily report image generator, implying a fixed Chinese/WeChat-specific language and locale context. There is no indication that users can choose another language or that the locale restriction is explicitly justified as a region-specific tool.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 93% confidence
- Finding
The file description is written entirely in Chinese and specifies a WeChat group chat daily report image generation workflow, but it does not indicate that language or locale is optional or user-selectable. Under the policy rule for natural-language violations, a skill that appears to require a specific language or locale without opt-in should be flagged unless the regional constraint is explicitly justified.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 89% confidence
- Finding
The file description is written to produce a WeChat group chat daily-report image and is entirely specified in Chinese, with no indication that users can choose another language or locale. Under the policy rule for natural-language violations, forcing a specific language without opt-in is a reportable issue unless the locale restriction is explicitly justified.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 92% confidence
- Finding
The file description is written in Chinese and specifies a WeChat chat-record daily report image generation workflow centered on a Chinese-language context, but it does not indicate that language/locale is optional or user-selectable. Under the policy, imposing a specific language or locale without opt-in is a natural-language policy concern unless the regional constraint is clearly documented and justified.
- Content
Intent-Code Divergence
Medium
- Category
- Not specified by scanner
- Confidence
- 97% confidence
- Finding
The Japanese description materially misstates the skill’s function, referring to weather-forecast analysis rather than WeChat group chat daily report generation. Misleading metadata can cause users, reviewers, or downstream agents to invoke the skill under false assumptions, increasing the chance of inappropriate data handling or unintended use of group-chat content.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The entire skill description is written in Japanese and provides no indication that users may choose another language or that the skill is intentionally limited to a Japanese-only or region-specific context. Under the policy, language constraints should be opt-in or clearly justified.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 75% confidence
- Finding
The skill description is written entirely in Chinese and is specifically scoped to WeChat group chat records, implying a fixed language/locale context. There is no indication that users can opt into another language or that the locale restriction is explicitly justified in the file.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 87% confidence
- Finding
The description is written as a Chinese-only skill purpose statement for generating a daily report image from WeChat group chats, with no indication that users may choose another language or locale. Under the policy rule, language constraints should either be optional or clearly documented as justified for a region-specific tool.
- Content
Static analysis
No suspicious patterns detected.