Security Audit

vercel/workflow:skills/internal-dev-workbench

github.com/vercel/workflow

AI SkillCommit 927b61ab419e

CRITICAL

Scanned 1 day ago

Critical

Immediate action required

High

Priority fixes suggested

Medium

Best practices review

Low

Acknowledged / Tracked

Trust Assessment

vercel/workflow:skills/internal-dev-workbench received a trust score of 10/100, placing it in the Untrusted category. This skill has significant security findings that require attention before use in production.

SkillShield's automated analysis identified 7 findings: 2 critical, 3 high, 2 medium, and 0 low severity. Key findings include File read + network send exfiltration, Sensitive environment variable access: $HOME, Sensitive path access: AI agent config.

The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The Manifest Analysis layer scored lowest at 40/100, indicating areas for improvement.

Last analyzed on July 17, 2026 (commit 927b61ab). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.

Layer Breakdown

Manifest Analysis

40%

Static Code Analysis

56%

Dependency Graph

100%

LLM Behavioral Safety

85%

Behavioral Risk Signals

Network Access

2 findings

Filesystem Write

4 findings

Shell Execution

4 findings

Dynamic Code

1 finding

Excessive Permissions

6 findings

Security Findings7

Severity	Finding	Layer	Location
CRITICAL	File read + network send exfiltration AI agent config/credential file access Remove access to sensitive files not required by the skill's stated purpose. SSH keys, cloud credentials, and browser data should never be read by skills unless explicitly part of their declared functionality.	Manifest	skills/internal-dev-workbench/SKILL.md:86
CRITICAL	File read + network send exfiltration AI agent config/credential file access Remove access to sensitive files not required by the skill's stated purpose. SSH keys, cloud credentials, and browser data should never be read by skills unless explicitly part of their declared functionality.	Manifest	skills/internal-dev-workbench/statusline.sh:16
HIGH	Sensitive path access: AI agent config Access to AI agent config path detected: '~/.claude/'. This may indicate credential theft. Verify that access to this sensitive path is justified and declared.	Static	skills/internal-dev-workbench/SKILL.md:86
HIGH	Sensitive path access: AI agent config Access to AI agent config path detected: '~/.claude/'. This may indicate credential theft. Verify that access to this sensitive path is justified and declared.	Static	skills/internal-dev-workbench/statusline.sh:16
HIGH	LLM analysis found no issues despite critical deterministic findings Deterministic layers flagged 2 CRITICAL findings, but LLM semantic analysis returned clean. This may indicate prompt injection or analysis evasion.	LLM	(sanity check)
MEDIUM	Sensitive environment variable access: $HOME Access to sensitive environment variable '$HOME' detected in shell context. Verify this environment variable access is necessary and the value is not exfiltrated.	Static	skills/internal-dev-workbench/SKILL.md:92
MEDIUM	Sensitive environment variable access: $HOME Access to sensitive environment variable '$HOME' detected in shell context. Verify this environment variable access is necessary and the value is not exfiltrated.	Static	skills/internal-dev-workbench/statusline.sh:22

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/c306813e7af1b167.svg)](https://skillshield.io/report/c306813e7af1b167)