Security audit

test-review

Security checks for vulnerabilities and agentic risk

Overview

The skill is a coherent test-review workflow, but it asks agents to run tests and install unpinned coverage tools without clear user approval or sandboxing guidance.

Install only if you are comfortable with an agent inspecting the repository and potentially running test, coverage, and tool-install commands. Use it in trusted repositories or a sandbox, and require approval before package installs or test execution.

A.I.G

Vulnerability Patterns

Insecure DependenciesIntroduces malicious components through unsafe dependency sources
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 (1)

T08 · Insecure Dependencies

Warning

Location: modules/coverage-analysis.md:18
Finding: Unpinned Third-Party Coverage Tool Installation
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
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: 95% confidence
Finding: The trigger list contains broad terms like testing, coverage, and quality, which are common in normal development conversations. This increases the chance the skill is invoked unintentionally, causing an agent to enter a workflow that includes command execution and external module loading in contexts where the user did not request it.
Content: No source excerpt is available for this finding.

Context-Inappropriate Capability

Low

Category: Not specified by scanner
Confidence: 90% confidence
Finding: The skill repeatedly instructs the agent/user to execute local shell commands and test tooling such as find, git diff, pytest -v, and related verification steps, even though the skill is framed as a review/audit workflow. In an agent setting, this expands the skill from passive analysis into active command execution against the local workspace, which can expose sensitive repository data, trigger untrusted test code, or cause unsafe side effects when used on adversarial projects.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.