Security Audit

knowledge-distillation

github.com/davila7/claude-code-templates

AI SkillCommit 458b11867eae

TRUSTED

Scanned 11 days ago

Critical

Immediate action required

High

Priority fixes suggested

Medium

Best practices review

Low

Acknowledged / Tracked

Trust Assessment

knowledge-distillation received a trust score of 83/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.

SkillShield's automated analysis identified 3 findings: 0 critical, 0 high, 2 medium, and 1 low severity. Key findings include Network egress to untrusted endpoints, Covert behavior / concealment directives, Unpinned Git Clone and Editable Install.

The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. All layers scored 70 or above, reflecting consistent security practices.

Last analyzed on February 12, 2026 (commit 458b1186). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.

Layer Breakdown

Manifest Analysis

91%

Static Code Analysis

93%

Dependency Graph

100%

LLM Behavioral Safety

100%

Behavioral Risk Signals

Network Access

2 findings

Shell Execution

1 finding

Security Findings3

Severity	Finding	Layer	Location
MEDIUM	Network egress to untrusted endpoints HTTP request to raw IP address Review all outbound network calls. Remove connections to webhook collectors, paste sites, and raw IP addresses. Legitimate API calls should use well-known service domains.	Manifest	cli-tool/components/mcps/devtools/figma-dev-mode.json:4
MEDIUM	Unpinned Git Clone and Editable Install The installation instructions include cloning a GitHub repository (`https://github.com/microsoft/LMOps`) and then installing it in editable mode (`pip install -e .`). This practice introduces a supply chain risk: 1. The `git clone` command does not specify a commit hash or tag, meaning future installations could pull different, potentially malicious, code if the upstream repository is compromised. 2. Installing a package in editable mode (`-e .`) from a cloned repository allows arbitrary code execution via `setup.py` or `pyproject.toml` if the repository contains malicious content. While the specified repository is from Microsoft, this pattern is a general security concern as it relies on the continuous integrity of the remote source. For production or security-sensitive environments, avoid `git clone` followed by `pip install -e .` from unpinned sources. Instead, consider: 1. Pinning the `git clone` to a specific commit hash or tag (e.g., `git clone <repo> && cd <repo> && git checkout <commit_hash>`). 2. Using a package manager to install a versioned package from a trusted registry if available. 3. Auditing the cloned repository's code before installation, especially `setup.py` or `pyproject.toml`.	Static	SKILL.md:30
LOW	Covert behavior / concealment directives Multiple zero-width characters (stealth text) Remove hidden instructions, zero-width characters, and bidirectional overrides. Skill instructions should be fully visible and transparent to users.	Manifest	cli-tool/components/mcps/devtools/jfrog.json:4

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/dde3c69dfd04cb5b.svg)](https://skillshield.io/report/dde3c69dfd04cb5b)