Back to skill

Security audit

Read dependency docs

Security checks for vulnerabilities and agentic risk

Overview

ClawScan rates this skill suspicious because it flags an unpinned CLI download and a dependency lookup issue, while analysis of one bundled script was only partial.

Consider the verdict’s recommendation not to install. Before reconsidering, seek a reviewed, pinned CLI version and confirmation that local or Git Cargo dependencies are excluded from public lookups. The evidence is incomplete: one bundled script was only partially 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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (5)

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · SKILL.md (reported line 17)May include surrounding context.

md
description: Optional llms.ink API key. The bundled helper sends it as a Bearer token; without it, anonymous limits apply.
---

Find the project's dependency manifests: `package.json`, `pyproject.toml`, `requirements*.txt`, `Cargo.toml` or `go.mod`, at the project root unless the user names a workspace member. If the project installs from a private registry (an `.npmrc` registry, a pip `--index-url`, a Cargo `registry =` entry), ask before looking anything up: dependency names are sent to the public registries.

When the user wants docs that match the installed versions kept in the repo (for example `.context/` referenced from AGENTS.md, refreshed in CI), use the llms.ink CLI instead of the steps below:

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 27)May include surrounding context.

md
List documentation sources with the bundled helper `scripts/ink.mjs`, choosing a new output path:

Skill declares no tool scope ('permissions' or 'allowed-tools') but code capabilities were detected: env.

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx -y @lukax/llms-ink'.

Medium
Category
MCP Rug Pull
Confidence
98% confidence
Finding

The command downloads and executes an unpinned npm CLI with automatic confirmation, so its executable contents can change without a skill update or review. A compromised publisher or malicious release could execute with the agent's filesystem and environment access, including available credentials; this is a supply-chain execution risk, although the referenced program is a CLI rather than an MCP server.

Content

No source excerpt is available for this finding.

Cargo dependencies with a local path or Git source are treated as public-registry packages when they also specify a version, contradicting the documented exclusion of those dependencies.

Medium
Category
Excessive Agency
Confidence
99% confidence
Finding

The Cargo exclusion condition allows dependencies with a path or Git source to proceed to public-registry lookup when a version is also present. This can disclose internal dependency names to crates.io and select documentation for an unrelated public package with the same name, violating the skill's explicit exclusion of local and Git dependencies.

Content

No source excerpt is available for this finding.