Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md to "Create a skill for X," and the IDE will generate the folder structure and `SKILL.md` automatically.
Security audit
Trae
Security checks for vulnerabilities and agentic risk
Overview
This is a documentation-style skill about TRAE IDE skills; it does not ship executable code, hidden behavior, persistence, or data access.
Reasonable to install as a TRAE skills guide. Before following its advice to import community skills, add scripts, use MCP, or create organization-wide skills, review the generated files and require explicit approval before anything executes or changes project configuration.
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
- 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 (6)
Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md to "Create a skill for X," and the IDE will generate the folder structure and `SKILL.md` automatically.
Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md to "Create a skill for X," and the IDE will generate the folder structure and `SKILL.md` automatically.
Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md to "Create a skill for X," and the IDE will generate the folder structure and `SKILL.md` automatically.
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The skill states that skills may be triggered automatically when the AI detects a context match, but it provides no guardrails for specificity, confirmation, or scope. In an IDE skill that discusses automation, sub-agents, and executable resources, broad auto-activation can cause the wrong workflow to load or run in response to ambiguous prompts, increasing the chance of unintended actions or unsafe context injection.
- Content
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 92% confidence
- Finding
Telling users they can ask the IDE to 'Create a skill for X' is a very broad natural-language trigger that can overlap with ordinary discussion about skills rather than an intentional command. In this skill's context, where generated skills may include instructions, scripts, and automation, ambiguous creation requests could lead to accidental generation of powerful or unsafe skill scaffolding from loosely phrased prompts.
- Content