T05 · Unauthorized Access and Privilege Escalation
Warning
- Location
SKILL.md:74- Finding
Unsafe Discovery and Plaintext Consolidation of Workspace Credentials
- Content
View full analysis
- Remediation
View remediation
Security audit
artifact-organizer
Security checks for vulnerabilities and agentic risk
Overview
The skill is a coherent file organizer, but it gives the agent under-scoped authority to find and relocate credentials into predictable workspace paths.
Review this skill before installing. Use it only when you intentionally want workspace files reorganized, and require explicit confirmation before it reads, moves, or summarizes anything that may contain credentials. Prefer a secret manager or encrypted store over plaintext files under secrets/, and keep any local secret paths excluded from source control, backups, logs, and indexing.
Vulnerability Patterns
- Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
- 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
- Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
- 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 (3)
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 96% confidence
- Finding
The trigger description is overly broad and includes generic phrases like '整理目录', '归类', and '帮我理一理结构', which can cause the skill to activate in loosely related situations. Over-triggering a filesystem-manipulating skill increases the chance of unintended file moves, restructuring, or handling of sensitive material when the user did not explicitly request workspace reorganization.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 83% confidence
- Finding
整个技能说明仅以中文提供，且没有说明用户可选择其他语言或该技能仅面向特定中文环境。按规则，未提供用户语言选择或明确、合理的地区性约束时，可能构成语言/locale policy violation。
- Content
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 90% confidence
- Finding
The body repeats permissive trigger criteria for vague user requests such as '整理一下' or '归类一下' without defining boundaries or exclusions. In context, this skill is designed to inspect and reorganize task artifacts, so ambiguous activation can lead to unnecessary traversal of project files and accidental movement of important or sensitive files.
- Content