Back to skill

Security audit

Write Adr

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward ADR-writing workflow that creates repository documentation files only after user confirmation.

Install this if you want an agent to create ADR documentation in your repository. Expect it to inspect repository history and existing ADRs, ask which detected decisions to write, then create or adjust markdown files under docs/adrs/. Review generated ADRs before committing them, especially because it depends on related ADR skills and a repo-local numbering script that are not included in this artifact.

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)

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

This markdown skill clearly generates ADR files, and later instructions also allow creating the ADR directory and adding or fixing frontmatter in generated files. The top-level description explains the workflow but does not explicitly warn users that running the skill will create and modify files in the repository.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
78% confidence
Finding

The skill requires date: YYYY-MM-DD as an actual date, which imposes a specific formatting convention in natural-language instructions. The file does not offer a user choice or explain that this locale/style constraint is required by a documented repository convention or regional compliance need.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.