Back to skill

Security audit

ken-review

Security checks for vulnerabilities and agentic risk

Overview

This skill only changes how the agent writes narrow code-review feedback and does not request execution, persistence, credentials, or data access.

Install only if you want a terse, opinionated simplification-focused review mode. Use a separate normal review for correctness, security, and performance, and avoid relying on quoted diff text to control whether the mode is active.

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 (1)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill defines deactivation phrases like "stop ken-review" and especially "normal mode" using ordinary natural language that could easily appear in unrelated user content or diffs under review. Because these phrases alter the skill's operating mode, an attacker could embed them in input to suppress the intended constrained review behavior or cause inconsistent handling of untrusted content.

Content

No source excerpt is available for this finding.