Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md node scripts/format-article.js input.md output.md
Security audit
Wechat Article Formatter
Security checks for vulnerabilities and agentic risk
Overview
This skill is a straightforward local WeChat article formatter with no hidden network, credential, persistence, or privilege behavior found.
Install only if you want a Chinese/WeChat-focused local article formatter. Use a new output filename or keep backups, because the formatter can overwrite the output file path you provide.
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
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 (8)
Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md node scripts/format-article.js input.md output.md
Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md node scripts/format-article.js input.md output.md
Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md node scripts/format-article.js input.md output.md
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 90% confidence
- Finding
The entire skill documentation is presented only in Chinese, including usage guidance and examples, with no indication that users may choose another language or that the skill is intentionally limited to a Chinese-speaking audience. This can violate language/locale policy where skills should not force a specific language without user opt-in or a clearly documented justification.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 94% confidence
- Finding
The manifest description and the entire user-facing documentation are written only in Chinese and target a Chinese-language WeChat publishing workflow, with no indication that users may choose another language or locale. Under the policy for natural-language violations, forcing a specific language without opt-in should be flagged unless the locale constraint is clearly documented and justified.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 96% confidence
- Finding
The file's natural-language descriptions and CLI messages consistently assume Chinese usage and a WeChat-publication context, with no option for users to select another language or locale. This constitutes a language/locale policy concern because the skill effectively forces one language without opt-in or a clearly documented justified constraint.
- Content
Missing User Warnings
Medium
- Category
- Not specified by scanner
- Confidence
- 94% confidence
- Finding
The script writes directly to a user-supplied output path with fs.writeFileSync() and does not check whether the destination already exists or prompt before overwriting it. In a CLI skill that processes local files, this can cause unintended destruction of user content if the wrong path is passed, especially because the tool is designed to write formatted output back to disk.
- Content
Static analysis
No suspicious patterns detected.