Ae4
Medium
- Category
- analysis-evasion
- Confidence
- 80% confidence
- Finding
Suspicious Unicode normalization or mixed-script content
- Content
Security audit
Cqi Special Process
Security checks for vulnerabilities and agentic risk
Overview
The skill is mostly a coherent Chinese CQI audit assistant, but it tells the agent to run a relative Python report script that is not included in the artifact.
Review before installing. The CQI workflow itself is disclosed and reasonable, but do not let the agent run `scripts/build_report.py` unless you know exactly which file it will execute and have reviewed it. Also confirm that Chinese report language and filenames match your audit process.
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
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- 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 (3)
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 90% confidence
- Finding
The skill description hardcodes Chinese-language interaction/output without offering a user language choice. This is not code-execution dangerous, but it can cause user misunderstanding, incorrect data entry, or audit/reporting errors when non-Chinese-speaking users rely on the generated assessment in a regulated quality context.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 88% confidence
- Finding
The skill mandates fixed Chinese output artifacts and filenames without user opt-in, which can create operational and compliance issues in multilingual environments. In an audit-document workflow, forced locale-specific filenames and report language can lead to mishandling, failed integrations, or reviewers acting on misunderstood content.
- Content