Security audit

api-connect-hub

Security checks for vulnerabilities and agentic risk

Overview

This skill is coherent with an API-integration purpose, but it asks for broad local and third-party automation authority without enough scoping or user-control safeguards.

Install only if you are prepared to supervise it as a write-capable integration tool. Review every connector source and permissions before installation, prefer Vault or an OS secret manager over local plaintext files, use least-privilege API tokens, and require a preview or explicit confirmation before syncs, webhook replays, token updates, connector publishing, or other actions that can change external systems.

A.I.G

Vulnerability Patterns

Insecure DependenciesIntroduces malicious components through unsafe dependency sources
Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
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

Findings (2)

T08 · Insecure Dependencies

Warning

Location: SKILL.md:90
Finding: Unverified Community Connector Installation Creates a Supply-Chain Risk
Content: View full analysis
Remediation: View remediation

T09 · Insecure Skill Coding Practices

Note

Location: SKILL.md:265
Finding: Local Credential Storage Guidance Lacks Required Access and Encryption Controls
Content: View full analysis
Remediation: View remediation

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 (2)

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The skill prominently advertises automated data synchronization, webhook handling, OAuth2 token refresh, and connector publishing, all of which can trigger outbound network actions, modify third-party systems, persist credentials, or expose tenant data boundaries. The documentation describes capabilities and benefits but does not clearly warn users that invoking the skill may perform write-capable operations against external services or transmit/store sensitive data, increasing the risk of unintended changes or data disclosure.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The quick-start section tells users to invoke the skill and provide inputs, but it does not disclose that the skill has read/exec/write tools and may perform automation on local resources or external APIs. In this context, omission is security-relevant because users may treat the skill as informational while it is actually capable of executing commands, modifying files, and triggering external side effects.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.