Security Audit
hig-project-context
github.com/sickn33/antigravity-awesome-skillsTrust Assessment
hig-project-context 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 2 findings: 0 critical, 0 high, 2 medium, and 0 low severity. Key findings include Excessive File System Read Permissions for Context Gathering, Potential Command Injection via 'Grep' Operation.
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 Findings2
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| MEDIUM | Excessive File System Read Permissions for Context Gathering The skill describes auto-discovering context from a broad range of project files, including 'Existing code' and performing an 'Accessibility audit' via 'Grep'. This implies requesting or assuming extensive read access to potentially all source code and configuration files within the user's repository. While intended for gathering design context, this broad access could inadvertently collect and consolidate sensitive information (e.g., internal logic, proprietary algorithms, specific framework usage) into `.claude/apple-design-context.md`. This consolidated file, though local, increases the attack surface and could become a high-value target for data exfiltration if the environment is compromised or if another skill with exfiltration capabilities gains access. Limit file access to only strictly necessary files and directories. Instead of 'Existing code', specify exact file types or paths. Implement explicit user consent for accessing broad categories of files. Consider redacting or filtering sensitive information before writing to `.claude/apple-design-context.md`. | LLM | SKILL.md:20 | |
| MEDIUM | Potential Command Injection via 'Grep' Operation The skill explicitly states it will perform an 'Accessibility audit' by 'Grep for accessibility modifiers/attributes.' This indicates the use of a shell command (`grep`). If the arguments or search patterns for this command are constructed using unsanitized user input or dynamically derived values from the project, it could lead to command injection, allowing an attacker to execute arbitrary commands on the host system. Avoid direct shell command execution where possible. If `grep` must be used, ensure all arguments, especially search patterns and file paths, are strictly validated and sanitized. Prefer using language-native file parsing and string searching functions over external shell commands to mitigate command injection risks. | LLM | SKILL.md:21 |
Scan History
Embed Code
[](https://skillshield.io/report/e5b511710cf0a19d)
Powered by SkillShield