Back to skill

Security audit

OKF Markdown

Security checks for vulnerabilities and agentic risk

Overview

The verdict is suspicious because the skill uses an unpinned GitHub package in commands, so the code it runs could change after review; scanner coverage is incomplete.

Before installing, consider whether you trust the GitHub package and are comfortable with its code running under your permissions. The scanner recommends using a reviewed fixed version; coverage was partial because several referenced paths could not be resolved, so the evidence does not establish that all runtime dependencies were inspected.

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
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (3)

MCP server referenced without pinned version: 'npx github'.

Medium
Category
MCP Rug Pull
Confidence
98% confidence
Finding

The ingest command executes a GitHub-hosted package without pinning an immutable revision, so changes to the repository or compromise of its maintainers could cause arbitrary code execution under the invoking user's permissions. Although this is a CLI rather than an MCP server, the underlying supply-chain risk is real; processing meeting transcripts also places potentially sensitive information within reach of compromised code.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx github'.

Medium
Category
MCP Rug Pull
Confidence
98% confidence
Finding

The validate command downloads and executes code from a mutable GitHub reference rather than a reviewed immutable revision. While the scanner incorrectly labels it an MCP server, a malicious upstream change could execute with the user's permissions, and the vault-validation workflow gives that code access to potentially sensitive notes.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx github'.

Medium
Category
MCP Rug Pull
Confidence
98% confidence
Finding

The graph command executes an unpinned GitHub package, allowing the executed code to change independently of this skill. This is not an MCP server declaration, but the supply-chain exposure remains: compromised code could read vault contents, alter files, or exfiltrate information using the invoking user's privileges.

Content

No source excerpt is available for this finding.