Back to skill

Security audit

Card Identity

Security checks for vulnerabilities and agentic risk

Overview

This skill only provides card-name disambiguation rules and does not include code, network behavior, credential access, persistence, or automatic execution.

Reasonable to install for card research workflows. Be aware it appears to depend on shared card-rule files not included in this artifact, so its behavior may require the companion shared rules to work as intended.

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
  • System Prompt LeakageDirect Leakage, Indirect Extraction, Tool-Based Exfiltration
  • 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)

Direct Prompt Extraction

High
Category
System Prompt Leakage
Confidence
85% confidence
Finding

Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.

Content

Scanner excerpt · SKILL.md (reported line 18)May include surrounding context.

md
4. Apply ambiguity rules from [../card-shared/card-identity-rules.md](../card-shared/card-identity-rules.md).
5. When the match is confident, keep identity in the hidden YAML keys from [../card-shared/normalization-rules.md](../card-shared/normalization-rules.md). When it is not confident, stop and return a numbered choice list.

## Output Rules

- Do not merge facts across variants.
- If a personal and business version both fit and the user did not specify which one, return both and stop.

Static analysis

No suspicious patterns detected.