Security audit

Error-Driven Evolution

Security checks for vulnerabilities and agentic risk

Overview

The skill has a coherent learning purpose, but it creates persistent agent rules from corrections and imports community guidance without enough approval, validation, or containment.

Install only if you are comfortable with the agent keeping workspace-level behavioral rules that affect later decisions. Review every new lesson before it is saved, avoid storing secrets or project-specific sensitive details, and pin or manually review any community rule files before using them as guidance.

A.I.G

Vulnerability Patterns

Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
Insecure DependenciesIntroduces malicious components through unsafe dependency sources
Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
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)

T02 · Agent Memory Poisoning

Error

Location: SKILL.md:12
Finding: Unvalidated Corrections Can Poison Persistent Agent Memory
Content: View full analysis
Remediation: View remediation

T08 · Insecure Dependencies

Warning

Location: SKILL.md:79
Finding: Unpinned Community Rules Create an External Instruction Supply-Chain Risk
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (4)

Anti-Refusal Statement

High

Category: Anti-Refusal
Confidence: 55% confidence
Finding: Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.
Content: Scanner excerpt · SKILL.md (reported line 59)May include surrounding context.
md
## How to Record 1. Stop. Don't apologize at length. 2. Identify the category. 3. Write the rule in imperative form. 4. Append to lessons.md (never overwrite).

Missing User Warnings

High

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The community-sharing feature encourages sending lessons to an external repository but does not require explicit user consent, preview, or strong safeguards against leaking sensitive operational details. 'Anonymized' is underspecified and can fail in practice, so mistakes, project names, internal paths, or user data could be disclosed externally.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The activation criteria are broad enough to trigger during many normal interactions, including generic corrections or routine decision-making. That increases the chance the skill will run unexpectedly, causing unsolicited file reads/writes and behavior changes without an explicit user request.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The skill instructs the agent to write to {workspace}/lessons.md automatically after errors or corrections, but it does not foreground that this modifies user workspace state. In environments where agents should minimize side effects, silent persistence can create integrity, privacy, and auditability issues.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.