Security audit

work-fllows

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent NocoBase workflow guide, but it gives under-scoped instructions for raw SQL automation and bulk workflow deletion that could modify or remove live business data.

Review this skill carefully before installing. Use it only in environments where the agent is allowed to create and enable NocoBase workflows, and require explicit confirmation before enabling workflows, running raw SQL, or deleting workflows by prefix. Prefer higher-level update nodes or parameterized SQL, test in non-production first, and preview any workflows matched for deletion.

A.I.G

Vulnerability Patterns

Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
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

Findings (2)

T09 · Insecure Skill Coding Practices

Error

Location: skill.md:80
Finding: SQL Injection Through Unvalidated Workflow Variable in Auto-Numbering Query
Content: View full analysis
Remediation: View remediation

T09 · Insecure Skill Coding Practices

Error

Location: skill.md:149
Finding: SQL Injection Through Unvalidated Workflow Variable in Scheduled Insurance Update
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
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 (2)

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: This section provides a ready-to-run pattern that combines raw SQL data modification with workflow enablement, but does not warn that enabling the workflow can immediately automate future writes to production data. In this skill's context, the danger is elevated because it is operational guidance for automation tooling, so unsafe examples can cause persistent, repeated data changes rather than a one-time mistake.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The skill explicitly recommends bulk cleanup via nb_delete_workflows_by_prefix("AM-") without any warning that this can delete multiple workflows at once. In an agent setting, that omission is dangerous because a user may request cleanup casually and the agent could perform irreversible destructive actions across many workflows.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.