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
Ops Coding Standards
Security checks for vulnerabilities and agentic risk
Overview
This is a Markdown-only coding-standards skill for Python/Django ops projects, with no commands, credentials, persistence, or data access requested.
Installers should expect this skill to influence Python/Django ops coding and review conversations. If that activation feels too broad, narrow the triggers before publishing or installing, but there is no inspected evidence of malicious behavior, persistence, credential handling, or command execution.
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 (6)
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
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
- 93% confidence
- Finding
The description indicates broad auto-activation for generic ops, Python, Django, and code-review requests. Overly broad activation can cause this skill to trigger in unrelated contexts, overriding more appropriate guidance and increasing the chance that operational advice is applied where it should not be, especially in sensitive coding or review workflows.
- Content
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 96% confidence
- Finding
The regex triggers use '(.*)' around short keywords, making them highly permissive and likely to match ordinary conversation fragments. This can lead to unintentional skill activation, prompt-context pollution, and misapplication of coding guidance in conversations that merely mention ops, Django, Python, or Celery, which is risky in an agentic environment because it changes behavior without clear user intent.
- Content