Back to skill

Security audit

Dental Office Marketing Copy

Security checks for vulnerabilities and agentic risk

Overview

The skill needs review because its broken compliance checker can miss risky claims and patient identifiers while reporting “No flags.”

Treat this as a drafting aid until the checker is fixed and tested. Do not treat “No flags” as compliance approval; have the practice review evidence, disclosures and consent before publication. Keep patient identifiers out of briefs and assess the optional Windows application separately.

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
  • 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 (3)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The script is related to dental marketing compliance, but its implemented scope falls materially short of the declared purpose. In run(), each pattern is lowercased and tested using pattern in low; no regex matching occurs despite the regex-formatted rules. Consequently, text such as 'painless' or 'cures' will not match its corresponding full pattern string, and the report can misleadingly say 'No flags.' The script also provides no copy-generation or substantive claim/testimonial verification functionality. Local input reading and report writing are ordinary supporting operations; there is no evidence of unrelated resource access or external transmission.

Content

No source excerpt is available for this finding.

Skill declares no tool scope ('permissions' or 'allowed-tools') but code capabilities were detected: file_write.

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

The compliance check does not deliver the manifest's promised checking of every health claim and testimonial.

Medium
Category
Excessive Agency
Confidence
99% confidence
Finding

The checker treats regex patterns as literal substrings instead of evaluating them, so ordinary claims such as 'painless' or 'cures' produce a misleading 'No flags' report. It also performs no testimonial verification or claim substantiation, falling short of the skill's stated checks. In dental marketing, reliance on this false assurance could allow misleading health claims or sensitive patient details to reach publication.

Content

No source excerpt is available for this finding.