Security Audit

frankxai/claude-skills-library:.grok/skills/harness-integration

github.com/frankxai/claude-skills-library

AI SkillCommit 93c4aad53fe8

CRITICAL

Scanned about 15 hours ago

Critical

Immediate action required

High

Priority fixes suggested

Medium

Best practices review

Low

Acknowledged / Tracked

Trust Assessment

frankxai/claude-skills-library:.grok/skills/harness-integration received a trust score of 49/100, placing it in the Untrusted category. This skill has significant security findings that require attention before use in production.

SkillShield's automated analysis identified 3 findings: 1 critical, 1 high, 1 medium, and 0 low severity. Key findings include File read + network send exfiltration, Sensitive path access: AI agent config, Out-of-workspace filesystem access (~/.claude and ~/.grok).

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 October 20, 2026 (commit 93c4aad5). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.

Layer Breakdown

Manifest Analysis

70%

Static Code Analysis

85%

Dependency Graph

100%

LLM Behavioral Safety

93%

Behavioral Risk Signals

Network Access

1 finding

Filesystem Write

3 findings

Shell Execution

1 finding

Excessive Permissions

3 findings

Security Findings3

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	.grok/skills/harness-integration/SKILL.md:6
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	.grok/skills/harness-integration/SKILL.md:6
MEDIUM	Out-of-workspace filesystem access (~/.claude and ~/.grok) The skill instructs the agent to use global home directory paths (~/.claude/skills and ~/.grok/skills) as a source of truth. Accessing directories outside the project workspace, especially sensitive configuration directories like ~/.claude which may contain session keys, history, or credentials, poses a security risk of data leakage or unauthorized modification of global agent configurations. Restrict the skill's scope to the local project workspace (e.g., .grok/ or .claude/ within the repository) and avoid accessing or modifying files in the user's home directory (~/).	LLM	SKILL.md:5

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/48d3b93e576113f9.svg)](https://skillshield.io/report/48d3b93e576113f9)