Security audit

Agent Contact Card

Security checks for vulnerabilities and agentic risk

Overview

The skill is a coherent markdown-only guide for agent contact cards, but it should be reviewed because it tells agents to trust remote card prose and try live webhook POSTs without enough consent or data-scope guardrails.

Install only if you are comfortable with agents fetching remote contact-card files and potentially contacting external endpoints. Before using it, treat fetched card text as untrusted, do not let it override your instructions, avoid sending personal or conversation data, and require a visible destination and payload confirmation before any webhook POST.

A.I.G

Vulnerability Patterns

Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
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

Findings (2)

T01 · Skill Instruction Hijacking

Error

Location: SKILL.md:22
Finding: Untrusted Remote Agent Cards Are Treated as Executable Instructions
Content: View full analysis
Remediation: View remediation

T09 · Insecure Skill Coding Practices

Error

Location: SKILL.md:154
Finding: Live Demo Encourages Unreviewed Data Transmission to a Third-Party Webhook
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (1)

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The skill explicitly encourages testing against a live third-party webhook endpoint and then sending POST requests, but it provides no warning about sharing prompts, metadata, or other potentially sensitive user or agent information with an external service. In an agent environment, this can lead to unintended disclosure of private data, logging by the remote service, or triggering actions on infrastructure outside the user's control.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.