Security audit

Database Migration Plan

Security checks for vulnerabilities and agentic risk

Overview

The skill is coherent and not deceptive, but its executable PostgreSQL migration examples contain real safety and correctness issues that could disrupt a production migration if copied directly.

Review this skill carefully before relying on it for production database work. It appears intended to help, but treat its SQL as a template requiring DBA review and PostgreSQL-specific correction before execution, especially for concurrent indexes, backfills, rollback steps, and destructive contract phases.

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

Warning

Location: SKILL.md:126
Finding: PostgreSQL Concurrent Index Operations Placed Inside Transaction Blocks
Content: View full analysis
Remediation: View remediation

T09 · Insecure Skill Coding Practices

Warning

Location: SKILL.md:183
Finding: Invalid PostgreSQL Batch Backfill Uses LIMIT Directly on UPDATE
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

Memory PoisoningPersistent Context Injection, Context Window Stuffing, Memory Manipulation
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

Findings (2)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 87% confidence
Finding: The manifest description says to use the skill when asked to 'plan a database migration,' 'document an expand/contract migration,' or 'coordinate a database schema update with a deployment.' In a markdown/manifest context, this acts like invocation guidance, but it does not define explicit trigger phrases, exclusions, or scope boundaries, making activation conditions somewhat open-ended.
Content: No source excerpt is available for this finding.

Context Window Stuffing

Medium

Category: Memory Poisoning
Confidence: 85% confidence
Finding: Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance or bypass safety boundaries.
Content: Scanner excerpt · SKILL.md (reported line 175)May include surrounding context.
App code change required:

text
// All INSERT and UPDATE operations must now set BOTH old_column and new_column // until Phase 3 is complete. This ensures new rows are populated during the backfill window.

Backfill script — batch processing:

Static analysis

No suspicious patterns detected.