Security Audit
error-debugging-multi-agent-review
github.com/sickn33/antigravity-awesome-skillsTrust Assessment
error-debugging-multi-agent-review received a trust score of 72/100, placing it in the Caution category. This skill has some security considerations that users should review before deployment.
SkillShield's automated analysis identified 1 finding: 1 critical, 0 high, 0 medium, and 0 low severity. Key findings include Untrusted content instructs LLM to open a local file.
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
Behavioral Risk Signals
Security Findings1
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | Untrusted content instructs LLM to open a local file The untrusted skill content contains a direct instruction to the host LLM: 'If detailed examples are required, open `resources/implementation-playbook.md`.' This is a prompt injection attempt, manipulating the LLM to access a local file within its environment. This could lead to data exfiltration if the file contains sensitive information or if the LLM's execution environment allows arbitrary file access. Remove or rephrase instructions that directly command the LLM to perform actions like 'open file', 'read content', or 'execute command' from untrusted skill definitions. Instead, the skill should describe *what* the LLM should do, and the LLM's internal tools/functions should handle file access securely and with appropriate permissions. | LLM | SKILL.md:18 |
Scan History
Embed Code
[](https://skillshield.io/report/7ed8ab78a7985410)
Powered by SkillShield