Security Audit

seo-content-auditor

github.com/sickn33/antigravity-awesome-skills

AI SkillCommit e36d6fd3b3f6

TRUSTED

Scanned 1 day ago

Critical

Immediate action required

High

Priority fixes suggested

Medium

Best practices review

Low

Acknowledged / Tracked

Trust Assessment

seo-content-auditor received a trust score of 85/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.

SkillShield's automated analysis identified 1 finding: 0 critical, 0 high, 1 medium, and 0 low severity. Key findings include Potential Data Exfiltration via Local File Access.

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 20, 2026 (commit e36d6fd3). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.

Layer Breakdown

Manifest Analysis

100%

Static Code Analysis

100%

Dependency Graph

100%

LLM Behavioral Safety

93%

Behavioral Risk Signals

Filesystem Write

1 finding

Excessive Permissions

1 finding

Security Findings1

Severity	Finding	Layer	Location
MEDIUM	Potential Data Exfiltration via Local File Access The skill's instructions, treated as untrusted content, include a directive to 'open' a local file, `resources/implementation-playbook.md`. If the underlying LLM has file-reading capabilities, this instruction could lead to the LLM accessing the contents of this file. Should the file contain sensitive or proprietary information, and a malicious user subsequently prompts the LLM to summarize or output its content, data exfiltration could occur. While conditional and requiring further user interaction for full exfiltration, the instruction itself creates a credible vector for unauthorized data access. Ensure that `resources/implementation-playbook.md` does not contain any sensitive or proprietary information. If the file is intended to be private, remove the instruction to 'open' it from the skill's description. Additionally, ensure that the LLM's file-reading tools (if any) are strictly sandboxed and have minimal necessary permissions, preventing access to unauthorized paths or sensitive data.	LLM	SKILL.md:16

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/81d37f6d1a2e4a88.svg)](https://skillshield.io/report/81d37f6d1a2e4a88)