Security Audit
mlops-engineer
github.com/sickn33/antigravity-awesome-skillsTrust Assessment
mlops-engineer 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 Skill instructs host LLM to open 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 | |
|---|---|---|---|---|
| MEDIUM | Skill instructs host LLM to open local file The skill contains a direct instruction for the host LLM to open a local file (`resources/implementation-playbook.md`). While this may be intended functionality for the skill to access its own resources, it demonstrates the skill's ability to issue commands to the host LLM. If the underlying file access mechanism is vulnerable to path traversal or if the content of the opened file is untrusted, this could lead to data exfiltration, command injection, or further prompt injection. Ensure the host LLM's file access mechanism is strictly sandboxed to prevent path traversal or access to unauthorized files. Validate the content of `resources/implementation-playbook.md` for any malicious instructions or data. Consider if direct file opening by the LLM is necessary, or if content could be pre-loaded or accessed via a more controlled API. | LLM | SKILL.md:22 |
Scan History
Embed Code
[](https://skillshield.io/report/6570f53521c42e93)
Powered by SkillShield