Back to skill

Security audit

Inclusive-Adaptation

Security checks for vulnerabilities and agentic risk

Overview

ClawScan marks this skill benign with high confidence: it found no AIG security issues, and Skillspector’s only reported issue is a privacy safeguard gap in a health and disability profiling workflow.

The verdict is benign, but consider whether you are comfortable sharing sensitive personal details with the workflow. The scanner recommends explaining why information is needed, allowing questions to be skipped, and using functional needs instead of diagnoses; avoid identifying details and be cautious about saving or sending profiles.

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
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • 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 (1)

The profiling workflow collects sensitive health and disability information without a privacy warning.

Medium
Category
Output Handling
Confidence
88% confidence
Finding

The skill explicitly elicits health, disability, pregnancy, recovery, and household-profile information through questionnaires, but provides no privacy notice, sensitive-data minimization requirements, or handling restrictions. Its ability to generate local reports creates a plausible risk of sensitive information being retained or disclosed unnecessarily, although the supplied file contains no explicit exfiltration instructions. Such information is relevant to accessibility planning, making collection legitimate but not eliminating the need for privacy safeguards.

Content

No source excerpt is available for this finding.