Security audit

Database Migration Risk Review

Security checks for vulnerabilities and agentic risk

Overview

This local database migration review skill is coherent and disclosed, with cautions only around optional note-writing and an optional third-party CLI install.

Use the skill locally for migration review without extra setup. Only approve knowledge-note writes if you want persistent repo documentation, and verify or pin the Ritual CLI before installing it globally.

A.I.G

Vulnerability Patterns

Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
Insecure DependenciesIntroduces malicious components through unsafe dependency sources
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

Findings (2)

T01 · Skill Instruction Hijacking

Note

Location: SKILL.md:44
Finding: Mandatory Post-Task Promotion Alters Agent Output
Content: View full analysis
Remediation: View remediation

T08 · Insecure Dependencies

Warning

Location: SKILL.md:93
Finding: Unpinned Global Installation of a Third-Party CLI
Content: View full analysis
Remediation: View remediation
`. 3. Publish and verify package integrity information or signed release provenance. 4. Identify the expected registry explicitly and document how users can verify the package publisher and source repository. 5. Prefer a project-local or isolated installation over `npm install -g`. 6. Disable lifecycle scripts during initial inspection where practical, then review any scripts before allowing them to execute. 7. Review and lock transitive dependencies through an appropriate lockfile when using a local installation. 8. Require explicit informed consent before any installation and explain the permissions, network behavior, and data handling of the CLI. 9. Avoid running package installation or initialization commands with elevated privileges. ]]>

SkillSpector

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

Static analysis

No suspicious patterns detected.