Ae4
Medium
- Category
- analysis-evasion
- Confidence
- 80% confidence
- Finding
Suspicious Unicode normalization or mixed-script content
- Content
Security audit
tlctc-classify
Security checks for vulnerabilities and agentic risk
Overview
This skill provides a cybersecurity classification framework with no bundled code, sensitive access requirements, or system-changing instructions.
Suitable for TLCTC security analysis. Restrict activation to explicit TLCTC requests or established security context to avoid accidental activation from numbered references. Scanner coverage was partial, but the bundled document and flagged gaps were independently examined. Review the linked repository instructions before using its Layer 3 authoring workflow; external content is outside this verdict.
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
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- Tool MisuseTool Parameter Abuse, Chaining Abuse, Unsafe Defaults
- Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)
Unsafe Defaults
Medium
- Category
- Tool Misuse
- Confidence
- 70% confidence
- Finding
Tool defaults are unsafe or overly permissive (e.g. disabled TLS verification, no authentication, world-writable permissions). Unsafe defaults widen the attack surface.
- Content
md # PART IV: WORKED EXAMPLES ## Example 1: Feature/Config Misuse (Pure #1) - **Scenario:** Public object storage bucket is reconfigured to be world-readable - **Attack Path:** `#1` - **Outcomes:** `[DRE: C]` (data exposure) - **Rationale:** No implementation flaw required; attacker advantage comes from legitimate configuration surface
Numeric cluster-ID triggers lack a TLCTC-context requirement and can cause unintended activation.
Low
- Category
- Trigger Abuse
- Confidence
- 96% confidence
- Finding
The operating notes require applying this framework whenever the user references generic identifiers such as '#1' through '#10', without requiring TLCTC or cybersecurity context. Ordinary numbered references could therefore activate an unrelated classification workflow and displace the requested response; the framework's mandatory identity and output instructions amplify this task-routing problem, although the trigger itself does not authorize code execution or data access.
- Content