Security audit

compliance-posture-intake

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed HIPAA compliance intake workflow that reads user-provided documents, researches relevant state obligations, and writes a report, with no evidence of hidden execution, exfiltration, or persistence beyond the expected output file.

Install only if you are comfortable sharing compliance policies, BAAs, risk assessments, or similar administrative records with the agent environment. Do not provide actual patient PHI. Treat the generated .docx as sensitive business/compliance material, store it in an appropriate location, and review any optional Rote product or consultation section before sharing externally.

A.I.G

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

SkillSpector

Vulnerability Patterns

Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
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 (4)

Description-Behavior Mismatch

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The manifest says the skill is compatible with any context that has access to rote-compliance-toolkit tools, implying those tools are sufficient for operation. But the implementation later mandates producing a .docx using a separate docx skill, and the allowed tools list does not mention such a capability. This is a semantic mismatch between the claimed portability/requirements and the actual execution requirements.
Content: No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The stated purpose is to conduct a structured compliance assessment and produce a posture snapshot and roadmap. The implementation adds optional sales-oriented behavior: mapping findings to the vendor's product modules and appending consultation or product links in the report and closing message. That capability is business development content, not necessary to perform the assessment itself.
Content: No source excerpt is available for this finding.

Description-Behavior Mismatch

Low

Category: Not specified by scanner
Confidence: 88% confidence
Finding: The manifest frames the skill as a HIPAA posture assessment centered on the Seven Elements and related HIPAA-focused analyses. The code expands scope by directing state-law privacy and breach-notification research for any named state and by adding a dedicated state-law section to the report. That is broader than a purely HIPAA posture intake, even though related.
Content: No source excerpt is available for this finding.

Missing User Warnings

Low

Category: Not specified by scanner
Confidence: 86% confidence
Finding: The skill instructs creation of a polished .docx report containing sensitive compliance posture details, organizational risk information, and potentially document-derived findings, but it does not require explicit user consent for file creation or warn about local persistence. In agent or shared-workspace contexts, silently writing such a report can increase exposure through residual files, sync services, backups, or unintended sharing.
Content: No source excerpt is available for this finding.