Security audit

summarize

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent summarization CLI wrapper, but users should be aware it relies on an external Homebrew-installed tool and may send submitted content to configured model or extraction providers.

Install this only if you are comfortable with Homebrew installing the third-party summarize CLI and with submitted content being processed by the configured model provider and optional extraction services. Avoid using it on sensitive local files or private URLs unless you have reviewed the provider settings and exposed only the API keys you intend to use.

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: SKILL.md:10
Finding: Unpinned Third-Party Homebrew Dependency
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
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: 95% confidence
Finding: The skill describes summarizing URLs and local files but does not warn users that content may be transmitted to external providers and that provider API keys are required. This lack of transparency can lead users to expose sensitive local documents or private URLs without informed consent, particularly since optional fallbacks like Firecrawl and Apify may introduce additional third-party sharing.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The trigger phrases are broad enough to match ordinary requests like asking what a link or video is about, which can cause the skill to activate in situations the user did not explicitly intend. Because this skill can process external URLs and local files through a CLI backed by third-party model providers, overbroad activation raises the risk of unintentional data disclosure or unnecessary external network access.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.