Security audit

eCRF Designer

Security checks for vulnerabilities and agentic risk

Overview

This skill appears intended to generate clinical form JSON, but its script can write to any user-supplied file path the running account can access.

Review before installing or running. Use only explicit workspace-relative output paths, avoid passing paths from untrusted input, and do not run it in directories where overwriting a writable file would matter until output path validation or overwrite protection is added.

A.I.G

Vulnerability Patterns

Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
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

Findings (1)

T09 · Insecure Skill Coding Practices

Warning

Location: scripts/main.py:75
Finding: Unrestricted Output Path Allows Arbitrary File Overwrite
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
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 (2)

Undeclared Tool Scope

Medium

Category: MCP Least Privilege
Confidence: 81% confidence
Finding: The skill metadata describes capabilities consistent with writing files, but it does not declare any explicit tool scope such as permissions or allowed-tools. This weakens enforcement and review boundaries, because an agent or runtime may permit broader file operations than users expect, increasing the chance of unintended or unsafe workspace modification.
Content: No source excerpt is available for this finding.

Missing User Warnings

Low

Category: Not specified by scanner
Confidence: 87% confidence
Finding: The skill states that local scripts may be executed and output files may be written, but it does not clearly warn users about the operational and safety consequences of running code or modifying local files. This can lead to unsafe use, especially in agentic environments where users may assume the skill is metadata-only and not realize it can change filesystem state.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.