Security Audit

segment-anything-model

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

segment-anything-model received a trust score of 75/100, 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, 1 high, 1 medium, and 1 low severity. Key findings include Network egress to untrusted endpoints, Covert behavior / concealment directives, Unpinned Git dependency in installation instructions.

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

85%

Dependency Graph

100%

LLM Behavioral Safety

100%

Behavioral Risk Signals

Network Access

2 findings

Filesystem Write

1 finding

Security Findings3

Severity	Finding	Layer	Location
HIGH	Unpinned Git dependency in installation instructions The `SKILL.md` documentation provides installation instructions that recommend installing the `segment-anything` library directly from a Git repository (`git+https://github.com/facebookresearch/segment-anything.git`) without specifying a fixed commit hash or tag. This practice introduces a significant supply chain risk, as the installed code can change if the remote repository is updated, potentially introducing vulnerabilities or malicious code without the user's explicit knowledge or consent. While the manifest lists `segment-anything` as a dependency, the explicit `git+` instruction in the documentation is a direct path for users to introduce this risk. Update the installation instructions to pin the Git dependency to a specific commit hash or tag (e.g., `git+https://github.com/facebookresearch/segment-anything.git@<commit_hash>`) to ensure reproducible and secure installations. Alternatively, if a stable PyPI package is available, recommend installing that with a pinned version (e.g., `segment-anything==X.Y.Z`).	Static	SKILL.md:30
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
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/379aaf342e595223.svg)](https://skillshield.io/report/379aaf342e595223)