Security Audit

modal-serverless-gpu

github.com/davila7/claude-code-templates

AI SkillCommit 458b11867eae

CAUTION

Scanned 11 days ago

Critical

Immediate action required

High

Priority fixes suggested

Medium

Best practices review

Low

Acknowledged / Tracked

Trust Assessment

modal-serverless-gpu received a trust score of 69/100, placing it in the Caution category. This skill has some security considerations that users should review before deployment.

SkillShield's automated analysis identified 5 findings: 0 critical, 0 high, 4 medium, and 1 low severity. Key findings include Network egress to untrusted endpoints, Covert behavior / concealment directives, Unpinned dependencies in skill environment.

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

79%

Dependency Graph

100%

LLM Behavioral Safety

100%

Behavioral Risk Signals

Network Access

1 finding

Security Findings5

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 dependencies in skill environment The skill's example code uses `pip_install` without pinning specific versions for several packages (e.g., 'transformers', 'torch', 'accelerate'). This can lead to supply chain risks where new versions of these packages might introduce vulnerabilities, breaking changes, or unexpected behavior. It also makes the build non-deterministic. Pin all dependencies to exact versions (e.g., `transformers==4.36.0`). Regularly review and update pinned versions to incorporate security patches and new features in a controlled manner.	Static	SKILL.md:48
MEDIUM	Unpinned dependencies in skill environment The skill's example code uses `pip_install` without pinning specific versions for several packages (e.g., 'torch', 'transformers'). This can lead to supply chain risks where new versions of these packages might introduce vulnerabilities, breaking changes, or unexpected behavior. It also makes the build non-deterministic. Pin all dependencies to exact versions (e.g., `torch==2.1.0`, `transformers==4.36.0`). Regularly review and update pinned versions to incorporate security patches and new features in a controlled manner.	Static	SKILL.md:109
MEDIUM	Unpinned dependencies in skill environment The skill's example code uses `pip_install` without pinning a specific version for the 'whisper' package. This can lead to supply chain risks where new versions of this package might introduce vulnerabilities, breaking changes, or unexpected behavior. It also makes the build non-deterministic. Pin all dependencies to exact versions (e.g., `whisper==1.0.0`). Regularly review and update pinned versions to incorporate security patches and new features in a controlled manner.	Static	SKILL.md:114
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/4cf3fec5a0401252.svg)](https://skillshield.io/report/4cf3fec5a0401252)