Back to skill

Security audit

Decision Engine Lite

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only decision-making guide with no tools, code execution, persistence, or sensitive data access.

Installers should treat this as a lightweight decision framework, not a security-sensitive integration. Be aware it links to an external paid/full version, but the reviewed artifact itself does not fetch content or require tools.

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
  • Memory PoisoningPersistent Context Injection, Context Window Stuffing, Memory Manipulation
  • 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
Findings (2)

Memory Manipulation

High
Category
Memory Poisoning
Confidence
80% confidence
Finding

Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.

Content

Scanner excerpt · SKILL.md (reported line 230)May include surrounding context.

Final Recommendation Output

markdown
## Decision: [Clear statement of what we're deciding]

**Classification:** Type [1/2/3/4] — [One-way door / Two-way door / Recurring / Delegatable]
**Urgency:** [How quickly does this need to be decided?]

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The example query "Help me decide whether to take this job offer" begins with a very broad conversational phrase that closely matches common everyday speech. In a markdown skill description, this can make activation scope ambiguous because the file does not clearly constrain which phrases should invoke the skill versus ordinary discussion about decisions.

Content

No source excerpt is available for this finding.