Security Audit

dotnet-backend

github.com/sickn33/antigravity-awesome-skills

AI SkillCommit e36d6fd3b3f6

TRUSTED

Scanned 2 days ago

Critical

Immediate action required

High

Priority fixes suggested

Medium

Best practices review

Low

Acknowledged / Tracked

Trust Assessment

dotnet-backend 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, 1 high, 0 medium, and 0 low severity. Key findings include Excessive Permissions Declared.

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

85%

Behavioral Risk Signals

Filesystem Write

1 finding

Shell Execution

1 finding

Dynamic Code

1 finding

Excessive Permissions

1 finding

Security Findings1

Severity	Finding	Layer	Location
HIGH	Excessive Permissions Declared The skill declares 'Bash', 'Write', and 'Edit' permissions in its manifest. While the skill describes building .NET applications and providing architectural advice, the 'Bash' permission grants the agent the ability to execute arbitrary shell commands, which is a highly privileged operation. 'Write' and 'Edit' permissions allow modification of any file within the agent's scope. The skill's description does not explicitly justify the need for such broad system-level access for its core function of code generation and advice. This significantly increases the attack surface for command injection or data exfiltration if the agent is compromised or misdirected. Review and restrict the 'allowed-tools' to the absolute minimum necessary for the skill's intended function. For a code generation and advice skill, 'Read' might be sufficient, or 'Write' for new files. If 'Bash' is truly required (e.g., for `dotnet` CLI commands), consider if a more constrained tool or a sandboxed environment could be used, or if specific commands can be whitelisted to reduce the risk.	LLM	SKILL.md:1

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/ad8cfea06e88bb23.svg)](https://skillshield.io/report/ad8cfea06e88bb23)