Back to skill

Security audit

ken

Security checks for vulnerabilities and agentic risk

Overview

This prompt-only coding skill is not malware, but it deliberately tries to stay active on every response and can push broad code rewrites beyond the stated coding-only scope.

Install only if you want this skill to shape the agent's coding behavior broadly. Be aware that it may favor rewrites, deletion of thin layers, and terse code-first responses unless you disable it with 'stop ken' or 'normal mode'.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (2)

Vague Triggers

High
Category
Not specified by scanner
Confidence
98% confidence
Finding

The skill declares itself active on every response by default and persistent until explicitly disabled, which is an unsafe activation model for an agent skill. This can cause the skill to influence unrelated tasks, override higher-priority user intent, and create cross-task behavior that is difficult to predict or contain.

Content

No source excerpt is available for this finding.

Whitespace Padding

Medium
Category
Prompt Injection
Confidence
70% confidence
Finding

Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.

Content

Scanner excerpt · SKILL.md (reported line 83)May include surrounding context.

md
## Intensity

| Level     | What changes                                                                                                                     |
| --------- | -------------------------------------------------------------------------------------------------------------------------------- |
| **lite**  | Advise: build what's asked, name the Thompson move (the rewrite, the brute-force cut) in one line. User picks.                   |
| **full**  | The loop enforced. Brute force until measured. Rewrite over third patch. Features argued in. Default.                            |