T09 · Insecure Skill Coding Practices
Warning
- Location
SKILL.md:95- Finding
Shell Command Injection Through Unquoted Directory Parameters
- Content
View full analysis
- Remediation
View remediation
Security audit
File Organizer Cn
Security checks for vulnerabilities and agentic risk
Overview
The skill is a legitimate file organizer, but its broad cleanup trigger and unsafe shell examples create review-worthy risk for local file changes.
Install only if you are comfortable with an assistant inspecting and reorganizing local files. Use it on one explicitly named folder at a time, review the proposed move/rename/delete plan, require confirmation before deletion, and ensure any shell commands treat directory paths as safe arguments rather than interpolated command text.
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
- 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 (5)
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The trigger phrase "清理" is broad and can match many routine requests unrelated to file organization, increasing the chance this skill is invoked in contexts the user did not intend. Because this skill can analyze, move, rename, and potentially delete files after interaction, ambiguous activation raises the risk of accidental exposure of sensitive file metadata or unintended destructive operations.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 91% confidence
- Finding
The title, description, category, and tags are written entirely in Chinese, indicating a locale-specific presentation, but the manifest does not document that the skill is intended only for Chinese-speaking users or provide an opt-in language choice. This can violate language/locale policy expectations when a skill implicitly forces one language without user selection or justification.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 74% confidence
- Finding
The metadata brands the skill as a China/Chinese variant and presents Chinese language first, but the file does not explain whether language behavior is optional or region-specific. That can create an implicit language or locale constraint without explicit user opt-in.
- Content
Vague Triggers
Low
- Category
- Not specified by scanner
- Confidence
- 77% confidence
- Finding
Although the full example is about Downloads, the instruction introduces invocation with a common everyday phrase that is not itself distinctive to this skill. This can make activation expectations unclear if trigger guidance is reused or interpreted loosely.
- Content
Vague Triggers
Low
- Category
- Not specified by scanner
- Confidence
- 85% confidence
- Finding
The metadata description advertises broad local file-management capabilities such as automatic classification, renaming, and duplicate cleanup without clearly constraining when the skill should activate or what boundaries apply. In an agent ecosystem, vague activation scope can cause unintended invocation on sensitive filesystem tasks, increasing the chance of overbroad actions or user-confusing behavior.
- Content