Back to skill

Security audit

Health & Safety Risk Assessments (UK)

Security checks for vulnerabilities and agentic risk

Overview

This skill is a document-generation aid for UK workplace risk assessments and does not request system access, persistence, credentials, or hidden execution.

Install only if you understand it produces drafts for UK contexts. Have a competent person review every assessment before use, and use qualified professional review for high-risk activities such as construction, COSHH, fire safety, confined spaces, and work at height.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The instruction 'UK English throughout' imposes a specific language/locale on all outputs. Under the policy, locale constraints should either be optional, user-selected, or clearly justified as region-specific; here the output-language requirement is mandatory and does not offer opt-in or flexibility.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The listing markets generated assessments as HSE-compliant, legally referenced, and ready for use, but does not clearly warn that outputs may be incomplete, inaccurate, or unsuitable without review by a competent person. In a health-and-safety and legal-compliance context, users may over-rely on the generated document, resulting in unsafe work practices, regulatory breaches, or injury if hazards and controls are missed.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.