Back to skill

Security audit

Multi-Dim Eval Framework Designer

Security checks for vulnerabilities and agentic risk

Overview

This markdown-only skill gives structured guidance for designing AI evaluation scorecards and does not show hidden execution, credential use, or persistence.

Install this if you want an assistant to help structure multi-dimensional AI system evaluations. Expect it to ask for examples, calibration cases, and data availability; only provide logs or system artifacts you are comfortable having the assistant analyze. Be aware that one referenced output template appears missing, so generated scorecards may rely on the examples instead.

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 (5)

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 80)May include surrounding context.

md
**Step 1: Surface the [12-axis MADEF reference](references/madef-axes.md)** to the user. Ask which axes feel relevant.

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 82)May include surrounding context.

md
**Step 1: Surface the [12-axis MADEF reference](references/madef-axes.md)** to the user. Ask which axes feel relevant.

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 142)May include surrounding context.

md
**Step 1: Surface the [12-axis MADEF reference](references/madef-axes.md)** to the user. Ask which axes feel relevant.

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 161)May include surrounding context.

md
**Step 1: Surface the [12-axis MADEF reference](references/madef-axes.md)** to the user. Ask which axes feel relevant.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The activation condition includes the broad phrase "Says 'tradeoffs'", which can cause the skill to trigger in many unrelated conversations that merely mention tradeoffs. Overly broad natural-language triggers increase the chance of accidental activation, leading to inappropriate steering of the interaction and possible context confusion, though this skill's content is not itself high risk.

Content

No source excerpt is available for this finding.