T09 · Insecure Skill Coding Practices
Warning
- Location
SKILL.md:40- Finding
Bearer API Token May Be Exposed Through Command-Line Configuration
- Content
View full analysis
- Remediation
View remediation
Security audit
Immens Mcp Fortress
Security checks for vulnerabilities and agentic risk
Overview
This skill is a coherent WordPress admin connector, but it gives an AI agent broad site-changing authority and uses a bearer token setup pattern without enough user-facing guardrails.
Install only with a narrowly scoped WordPress Access Point, preferably on staging first. Treat the API key like a password, avoid pasting it into shared shells or logs, use IP allowlisting and audit logs, and require human approval for deletes, user changes, WooCommerce/customer/order changes, plugin settings, and Code Snippets operations.
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
- Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
- 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)
Missing User Warnings
Medium
- Category
- Not specified by scanner
- Confidence
- 93% confidence
- Finding
The skill advertises broad WordPress administrative capabilities including create, update, delete, moderation, user management, plugin integrations, and cache flushing, but does not include any caution that these operations can cause destructive, site-wide, or irreversible changes. In a skill that enables remote control over a production CMS, omission of impact warnings increases the chance of unsafe use, accidental destructive actions, and over-broad delegation to an AI agent.
- Content
Missing User Warnings
Medium
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The configuration and capability sections instruct users to supply a bearer API key for remote administrative access to a WordPress site, but they do not warn about secure secret handling, the sensitivity of the token, or the risks of granting an AI agent broad remote admin functionality. This is dangerous because users may paste production credentials into insecure environments, overexpose highly privileged tokens, or connect agents to live sites without understanding the security implications.
- Content
Static analysis
No suspicious patterns detected.