Security Audit
startup-business-analyst-business-case
github.com/sickn33/antigravity-awesome-skillsTrust Assessment
startup-business-analyst-business-case received a trust score of 82/100, 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, 1 high, 1 medium, and 0 low severity. Key findings include Excessive 'Bash' permission declared for document generation skill, Potential Command Injection via unsanitized user input in filename.
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 | |
|---|---|---|---|---|
| HIGH | Excessive 'Bash' permission declared for document generation skill The skill declares 'Bash' permission, which allows arbitrary command execution. For a skill primarily focused on generating a business case document, this permission is excessive and introduces significant risk. While the provided SKILL.md does not explicitly show Bash commands being used, the capability exists, and could be exploited if the skill's internal logic or subsequent user interactions lead to unsanitized shell execution. Review and remove the 'Bash' permission if not strictly necessary for the skill's core functionality. If Bash is genuinely required, ensure all inputs to Bash commands are rigorously sanitized and commands are executed within a highly restricted environment. | LLM | SKILL.md:1 | |
| MEDIUM | Potential Command Injection via unsanitized user input in filename The skill instructs the LLM to save the generated business case with a filename format `business-case-[company-name]-YYYY-MM-DD.md`, where `[company-name]` is derived from user input. Given the declared 'Bash' and 'Write' permissions, if the LLM constructs a shell command or file path using this user-provided company name without proper sanitization, a malicious user could inject shell commands (e.g., `MyCompany; rm -rf /`) leading to arbitrary code execution or file system manipulation. Implement robust sanitization and validation for all user-provided inputs, especially those used in file paths or shell commands. Ensure that the LLM is explicitly instructed to escape or disallow special characters in filenames derived from user input before using them with file system operations or shell commands. | LLM | SKILL.md:261 |
Scan History
Embed Code
[](https://skillshield.io/report/e3018d1e6e7b573a)
Powered by SkillShield