Security Audit
outlook-automation
github.com/sickn33/antigravity-awesome-skillsTrust Assessment
outlook-automation 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 enables download of sensitive attachments.
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 enables download of sensitive attachments The skill documentation describes the `OUTLOOK_DOWNLOAD_OUTLOOK_ATTACHMENT` tool, which allows the agent to download attachments from a user's Outlook mailbox. This grants broad access to potentially sensitive user files. While this is the intended functionality of the tool, it represents an excessive permission if not carefully controlled, as a malicious prompt could instruct the agent to download and potentially exfiltrate sensitive documents. Implement strict access controls or user confirmation for sensitive operations like downloading attachments. Ensure the agent's output channels are secure and do not inadvertently exfiltrate downloaded data. | LLM | SKILL.md:40 |
Scan History
Embed Code
[](https://skillshield.io/report/368f824444d47386)
Powered by SkillShield