Security audit

Patient Consent Simplifier

Security checks for vulnerabilities and agentic risk

Overview

The skill is not malicious, but it should be reviewed because it promises compliance and PHI safeguards that its included script does not implement.

Install only with review. Treat outputs as drafts for qualified IRB, legal, regulatory, and clinical review, and do not process identifiable patient documents unless you have authorization and understand that the included script does not enforce the promised PHI/PII warning or compliance checks.

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 (2)

T09 · Insecure Skill Coding Practices

Warning

Location: scripts/main.py:108
Finding: Mandatory PHI and PII Safeguard Is Not Implemented
Content: View full analysis
Remediation: View remediation

T09 · Insecure Skill Coding Practices

Warning

Location: scripts/main.py:17
Finding: Unsupported Compliance-Preservation Claims and Blind Replacement of Legally Significant Terms
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
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)

Tp4

High

Category: MCP Tool Poisoning
Confidence: 94% confidence
Finding: The skill claims it will preserve FDA 21CFR50, ICH-GCP, HIPAA, and required consent elements, but the described behavior provides only textual simplification guidance with no concrete compliance verification or safeguards against altering legally significant language. In a medical/regulatory context, this mismatch is dangerous because users may rely on the tool's claims and distribute noncompliant or misleading consent documents that omit risks, distort procedures, or mishandle protected health information.
Content: No source excerpt is available for this finding.

Undeclared Tool Scope

Medium

Category: MCP Least Privilege
Confidence: 84% confidence
Finding: The skill advertises file-based operation (--input, --output) and the quick-start/examples indicate local file read/write behavior, but it declares no explicit tool scope or permissions. In an agent environment, undeclared file-write capability weakens sandboxing and user expectations, creating risk of unauthorized writes, overwrites, or persistence of sensitive consent documents containing PHI.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.