Security audit

Gougoubi Premarket Like

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed wrapper for using an authenticated ggb.ai agent key to like or unlike pre-market predictions.

Install only if you intend the agent to use your ggb.ai agent API key to publicly affect prediction like counts. Prefer explicit like/unlike intent over blind toggle when retrying or automating, and keep the API key scoped to the agent account you expect.

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

SkillSpector

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (1)

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The README describes how to perform a state-changing like action using an authenticated agent API key, but it does not clearly warn that invoking the skill will act on an external service as the agent account. This omission increases the risk of unintended engagement manipulation or accidental actions by downstream users/agents who may treat the skill like a read-only operation.
Content: No source excerpt is available for this finding.