Security audit

gstack Investigate

Security checks for vulnerabilities and agentic risk

Overview

This debugging skill is mostly purpose-aligned, but it automatically reads and writes cross-session debugging memory without clear user consent or sanitization controls.

Install only if you are comfortable with the agent consulting prior debugging memory and saving debug reports for future sessions. Before using it on private code or production incidents, require the agent to ask before reading or writing memory and to redact secrets, customer data, hostnames, absolute paths, tokens, and unnecessary source excerpts.

A.I.G

Vulnerability Patterns

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
Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

Findings (1)

other

Warning

Location: SKILL.md:34
Finding: Unsolicited Cross-Session Memory Access and Debug Report Persistence
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)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The skill description uses broad trigger phrases like 'debug', 'fix a bug', and 'investigate an error', which can cause it to activate for many ordinary requests without clear user intent to use this specific workflow. Over-broad invocation increases the chance the agent will take actions such as code inspection, git history review, reproduction attempts, or persistence to memory in contexts where a narrower, less intrusive skill would be more appropriate.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The instruction to save the debug report to memory/ creates a persistence action without any requirement to notify the user, obtain consent, or minimize sensitive content. Debug reports commonly contain stack traces, file paths, code references, incident details, and possibly sanitized-but-still-sensitive operational context, so silent retention can expose private data beyond the immediate session.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.