T09 · Insecure Skill Coding Practices
Warning
- Location
SKILL.md:36- Finding
API Key Exposed Through MCP URL Query Parameter
- Content
View full analysis
- Remediation
View remediation
Security audit
Social Media Scheduler - schedule, publish, cross-post, & auto-post social media posts with text, images, video uploads, Reels, Stories, Shorts and carousels to Instagram, Facebook, Threads, LinkedIn, LinkedIn Pages, X, TikTok, Pinterest and YouTube via WoopSocial MCP for AI agents
Security checks for vulnerabilities and agentic risk
Overview
The skill matches its stated social-media publishing purpose, but its API-key setup method risks exposing credentials for accounts that can publish public posts.
Prefer the OAuth setup and avoid the API-key URL method. Install only if you are comfortable giving the agent the ability to create, schedule, upload media for, and delete social-media resources when you explicitly ask it to, and review target accounts, content, and schedule carefully before public posting.
Vulnerability Patterns
- 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
- Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
Findings (1)
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 (4)
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The skill advertises very broad activation criteria such as 'use whenever the user wants to post, schedule, queue, cross-post, bulk-schedule, draft, or auto-publish social content,' which increases the chance the agent invokes it in loosely related contexts. Because this skill can trigger real external publishing actions, overbroad routing materially raises the risk of unintended posting to public third-party platforms.
- Content
Missing User Warnings
Medium
- Category
- Not specified by scanner
- Confidence
- 89% confidence
- Finding
The skill enables publishing and auto-publishing to multiple third-party social networks, but the description does not prominently warn that content will be transmitted externally and may become publicly visible. In a tool that can make irreversible public-facing changes, lack of up-front disclosure increases the risk of users or orchestration layers invoking it without appreciating the external impact.
- Content
External Transmission
Medium
- Category
- Data Exfiltration
- Confidence
- 50% confidence
- Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
- Content
sh openclaw mcp add woopsocial \ --url https://api.woopsocial.com/mcp \ --transport streamable-http \ --auth oauth
External Transmission
Medium
- Category
- Data Exfiltration
- Confidence
- 94% confidence
- Finding
The documentation instructs users to place an API key directly in the MCP URL query string. Query-parameter secrets are commonly exposed through shell history, process listings, logs, config files, screenshots, and proxy/server logging, making credential leakage significantly more likely than header- or secret-store-based authentication.
- Content
sh openclaw mcp add woopsocial \ --url https://api.woopsocial.com/mcp?api_key=YOUR_API_KEY \ --transport streamable-http
Static analysis
No suspicious patterns detected.