T09 · Insecure Skill Coding Practices
Warning
- Location
scripts/optimizer.sh:130- Finding
Unescaped User Input Allows JSON Structure Injection
- Content
View full analysis
- Remediation
View remediation
Security audit
Juejin Article Optimizer
Security checks for vulnerabilities and agentic risk
Overview
This skill is a disclosed Juejin-focused writing helper with a local script and no evidence of posting, credential use, persistence, or hidden data movement.
Install only if you want Juejin-oriented, Chinese-market article optimization. Keep final publishing under your control, review any generated promotional language, and avoid feeding the script's JSON output directly into automation unless it is re-serialized or strictly validated first.
Vulnerability Patterns
- Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
- 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 (5)
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 92% confidence
- Finding
The skill explicitly adapts content into Chinese for Juejin publication without clearly requiring user opt-in for language transformation. This can override user intent, cause unintended disclosure or repurposing of content into another language/audience, and create compliance or policy issues if the user expected analysis only rather than full cross-language adaptation.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 84% confidence
- Finding
This manifest-type file includes natural-language guidance and examples centered on Chinese content, including the title 'Juejin Article Optimizer Input' and Chinese-only example article titles and tags. Because the schema does not indicate that the skill is region-specific or that users may provide other languages, it appears to impose a locale/language expectation without explicit opt-in or justification.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 90% confidence
- Finding
The script description, examples, and later generated outputs are all explicitly tailored to Chinese-language Juejin content, and the tool does not offer any language or locale selection. This can violate language/locale policy because it effectively forces a specific language and audience context without user opt-in or a clearly documented justified regional limitation.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 90% confidence
- Finding
The manifest hard-codes a Chinese trigger phrase ("帮我优化这篇文章") as the primary success path without presenting language choice or user opt-in. This can exclude users, bias invocation behavior, and create prompt-steering that reduces user control, though it is not a direct code-execution or data-exfiltration issue.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 83% confidence
- Finding
This manifest-like JSON includes Chinese-only content in multiple title patterns and bilingual labels oriented to a specific locale, but provides no indication that the language choice is optional or region-specific. Under the policy, forcing a specific language or locale without user opt-in can be a natural-language policy violation.
- Content
Static analysis
No suspicious patterns detected.