Back to skill

Security audit

FHIR endpoint preflight

Security checks for vulnerabilities and agentic risk

Overview

This is a narrow, disclosed FHIR endpoint preflight helper, with the main cautions being its PowMCP connection and unpinned setup command.

Install only if you are comfortable connecting to PowMCP and sending public FHIR endpoint details to that service. Do not use credential-bearing, private, or patient-data URLs, and prefer pinned or otherwise verified install sources where your environment supports them.

Vulnerability Patterns
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • 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)

T08 · Insecure Dependencies

Warning
Location
SKILL.md:34
Finding
Unpinned Third-Party Package Execution Through npx## Vulnerability Details **File Location**: `SKILL.md:34-37` **Vulnerability Type**: Unpinned and mutable third-party dependency execution **Risk Level**: Medium ```markdown ## Connect once ``` npx skills add powmcp/skills --skill preflight-client-endpoint-before-integration ``` ``` ### Technical Analysis The installation instructions invoke the third-party `skills` package through `npx` without specifying an exact package version or integrity digest. If the package is not already available locally, `npx` can retrieve and execute its currently published version. The `powmcp/skills` source is likewise referenced without an immutable commit identifier or reviewed release version. Consequently, the code executed during installation can change after this Skill has been reviewed. Compromise of the npm package, its publisher account, or the referenced Skill repository could introduce malicious installation behavior through a later release. This is a supply-chain risk rather than evidence that the currently referenced package is malicious. ### Attack Path 1. An attacker compromises the npm package, its publishing credentials, or the mutable `powmcp/skills` source. 2. The attacker publishes a modified package or repository revision containing malicious installation logic. 3. A user follows the documented `npx skills add ...` command. 4. `npx` resolves and downloads the mutable package version, while the installer resolves the mutable Skill source. 5. Attacker-controlled code executes in the user's environment during installation or subsequent Skill loading. 6. The payload operates with the permissions of the user who ran the command. ### Impact Assessment Successful exploitation could allow arbitrary code execution with the installing user's privileges. Depending on that user's access and the behavior of the compromised package, the payload could read or alter accessible files, environment variables ...[truncated 251 chars]
Remediation
## Remediation Suggestions 1. Pin the `skills` CLI to a reviewed exact version, for example by using an explicit package version rather than allowing `npx` to resolve the latest release. 2. Pin `powmcp/skills` to an immutable commit hash, signed tag, or versioned release supported by the installer. 3. Use a lockfile and verify package integrity hashes where the installation workflow supports them. 4. Disable automatic acceptance of newly published versions and require security review before updating either dependency. 5. Prefer a trusted, preinstalled CLI in controlled environments instead of downloading executable package content at invocation time. 6. Run installation with the minimum required user privileges and without unnecessary credentials or sensitive environment variables. 7. Document the expected package version, source revision, and checksum so users can verify the reviewed artifact before execution.
Vulnerability Patterns
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Rp1

Medium
Category
MCP Rug Pull
Confidence
94% confidence
Finding
The skill instructs users to install and execute a remote package via `npx skills add powmcp/skills` without pinning an exact version. This creates a supply-chain risk: if the upstream package or dependency tree changes or is compromised, users may execute unintended code when following the setup instructions.

Vague Triggers

Medium
Confidence
91% confidence
Finding
The skill enables allow_implicit_invocation without any visible trigger constraints, exclusions, or additional policy gating. That can cause the agent to automatically invoke an external MCP tool based on loosely related user input, sending user-supplied FHIR endpoint URLs or surrounding context to a third-party service without an explicit invocation decision, which increases the risk of unintended data disclosure and tool misuse.

Static analysis

No suspicious patterns detected.