Security audit

Monitor Content Decay & Score Refresh Opportunities Automatically

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent content-audit helper, but users should treat its analytics, WordPress, and Slack integrations as sensitive business-data sharing.

Install only if you are comfortable connecting marketing analytics and content systems. Use read-only or least-privilege accounts where possible, restrict any WordPress application password, send Slack reports only to a controlled channel, and confirm whether SERP_API_KEY or SERPAPI_KEY is the intended variable name.

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
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (4)

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 7)May include surrounding context.
md
API_KEY"],"bins":["python3","curl"]},"os":["macos","linux","win32"],"files":["SKILL.md"],"emoji":"📉"}}

Intent-Code Divergence

Low

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The metadata declares a required environment variable named SERP_API_KEY, but the configuration section later documents SERPAPI_KEY instead. This is an active documentation-to-spec divergence that can mislead users about what credential the skill actually expects.
Content: No source excerpt is available for this finding.

Missing User Warnings

Low

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The skill references WordPress REST API access and application passwords without clearly warning that the skill may receive site content, metadata, and reusable credentials. In this context, granting WordPress API access can expose unpublished or sensitive content and, if overprivileged credentials are used, could expand impact beyond read-only analysis depending on the connected account's permissions.
Content: No source excerpt is available for this finding.

Missing User Warnings

Low

Category: Not specified by scanner
Confidence: 88% confidence
Finding: The skill advertises Slack delivery of audit results without warning that content performance data, URLs, rankings, and potentially sensitive business metadata may be transmitted to a third-party service. In this context, the exported data is not usually secret at the credential level, but it can still disclose internal editorial priorities, traffic trends, and competitive weaknesses if sent to an external workspace or misconfigured webhook.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.