Tp2
High
- Category
- MCP Tool Poisoning
- Confidence
- 85% confidence
- Finding
Mixing characters from multiple Unicode scripts in a single identifier is a common technique to create visually ambiguous tool names.
- Content
Security audit
Deslop
Security checks for vulnerabilities and agentic risk
Overview
This is a text-rewriting skill for making articles sound less AI-written, with no evidence of hidden execution, credential access, persistence, or data exfiltration.
Install only if you want a mostly Chinese-language writing assistant for revising articles or documents to reduce AI-like phrasing. Review changes before applying them, especially because the triggers may activate on some general article-rewriting requests.
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
- Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
- MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (10)
Tp2
High
- Category
- MCP Tool Poisoning
- Confidence
- 85% confidence
- Finding
Mixing characters from multiple Unicode scripts in a single identifier is a common technique to create visually ambiguous tool names.
- Content
Tp2
High
- Category
- MCP Tool Poisoning
- Confidence
- 85% confidence
- Finding
Mixing characters from multiple Unicode scripts in a single identifier is a common technique to create visually ambiguous tool names.
- Content
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 96% confidence
- Finding
The manifest trigger list includes the standalone phrase "人味", which is a common, generic expression and not specific to this skill's invocation context. Although the file provides usage guidance elsewhere, the trigger itself is broad enough to cause unintended activation in ordinary writing discussions.
- Content
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 88% confidence
- Finding
This regex-style trigger covers broad requests to rewrite articles, but the skill is intended specifically for de-slopping or removing AI-like writing patterns rather than general rewriting. Because the trigger does not constrain the request to AI-style cleanup, it could overlap with ordinary editing or rewriting tasks.
- Content
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 91% confidence
- Finding
The phrase matches broad discussions about article style, which can include many unrelated editing, branding, or tone-adjustment tasks. The trigger lacks explicit constraints tying activation to AI-writing symptoms, increasing the chance of accidental invocation.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 90% confidence
- Finding
The document title and introductory description are entirely in Chinese and provide no indication that other languages are supported or that the user can choose a preferred language. Under the policy criteria, forcing a specific language without opt-in is a natural-language policy concern.
- Content
Overly Broad Trigger
Low
- Category
- Trigger Abuse
- Confidence
- 70% confidence
- Finding
Overly Broad Trigger: '人味' is too short and may match unintended inputs
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
This markdown file contains user-facing guidance exclusively in Chinese, and nowhere indicates that the skill is intended only for Chinese-speaking users or that another language option is available. Under the language/locale policy, forcing a specific language without user opt-in is a natural-language policy concern.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 83% confidence
- Finding
This markdown file contains user-facing instructional content exclusively in Chinese, and there is no indication that Chinese is an optional or region-specific presentation choice. Under the policy rule for natural-language violations, forcing a single language without opt-in can be a locale policy issue.
- Content