Back to skill

Security audit

Client Site Handoff Report

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed handoff-report workflow that checks public page links through a remote PowMCP service, with install and implicit-use cautions but no evidence of hidden or harmful behavior.

Install only if you are comfortable connecting a remote PowMCP link-checking service and sending it the public page URL being reviewed. Avoid private, authenticated, or secret-bearing URLs; verify or pin the npx installer/source if your environment requires stronger supply-chain controls; remove the MCP connection later if you do not want it available for future sessions.

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:35
Finding
Unpinned Package Execution Through npx## Vulnerability Details **File Location**: `SKILL.md`, line 35 **Vulnerability Type**: Supply-chain risk caused by an unpinned executable dependency **Risk Level**: Medium ### Vulnerable Code ```sh npx skills add powmcp/skills --skill produce-client-site-handoff-report ``` ### Technical Analysis The documented installation command invokes `npx` without pinning the `skills` package to a reviewed version or integrity hash. Depending on the local package-manager state, `npx` can download the package from the configured registry and execute its current release. This creates a mutable execution boundary: the code run by a user may differ from the code that existed when this Skill was reviewed. Compromise of the package, its publisher account, or the configured package registry could therefore introduce attacker-controlled installation behavior. The issue is limited to users who run this installation command. The audit found no evidence that the Skill silently invokes the command, and no bundled malicious script was identified. ### Attack Path 1. An attacker compromises the package publisher, package distribution channel, or registry resolution path for the unversioned `skills` package. 2. The attacker publishes a malicious release or causes the package name to resolve to attacker-controlled content. 3. A user follows `SKILL.md` and runs the documented `npx skills add ...` command. 4. `npx` retrieves the current, unreviewed package release. 5. Package entry-point or installation code executes with the privileges of the invoking user. 6. The malicious package can access resources available to that user and modify files permitted by the user's operating-system permissions. ### Impact Assessment Successful exploitation could provide arbitrary code execution under the invoking user's account. The resulting scope could include reading or changing user-accessible files, accessing credentials exposed to the process, modifying local development configuration, or i ...[truncated 656 chars]
Remediation
## Remediation Suggestions 1. Pin the executable package to a specific, reviewed version, for example by using the package manager's exact-version syntax rather than resolving the latest release. 2. Use a lockfile and verified integrity metadata where supported. 3. Document the exact expected registry and package identity to reduce dependency-confusion and registry-substitution risk. 4. Prefer a reviewed local installation over automatic download-and-execute behavior. 5. Instruct users to inspect the resolved package version and provenance before running it. 6. Establish a controlled update process in which new dependency versions are reviewed and tested before the documented pin is changed. 7. Avoid recommending elevated execution and explicitly state that the installation command should run with ordinary user privileges.
Vulnerability Patterns
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Rp1

Medium
Category
MCP Rug Pull
Confidence
92% confidence
Finding
The skill instructs users to run `npx skills add powmcp/skills --skill produce-client-site-handoff-report` without pinning an exact package version. That allows whatever version is current at execution time to be fetched and run, creating a supply-chain risk if the package is updated maliciously or unexpectedly changed.

Vague Triggers

Medium
Confidence
92% confidence
Finding
The skill enables allow_implicit_invocation without defining any trigger constraints or exclusions, which increases the chance that the agent invokes an external MCP service in situations the user did not explicitly request. Because this skill reaches out to a remote link-checking service, implicit activation can cause unintended external network access, transmission of site URLs or related context, and tool use outside the intended handoff-review workflow.

Static analysis

No suspicious patterns detected.