Trust Assessment
gitflow received a trust score of 65/100, placing it in the Caution category. This skill has some security considerations that users should review before deployment.
SkillShield's automated analysis identified 2 findings: 1 critical, 0 high, 1 medium, and 0 low severity. Key findings include File read + network send exfiltration, Shell command execution via recommended git alias.
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 13, 2026 (commit 13146e6a). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings2
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | File read + network send exfiltration Package manager / git credential file access Remove access to sensitive files not required by the skill's stated purpose. SSH keys, cloud credentials, and browser data should never be read by skills unless explicitly part of their declared functionality. | Manifest | skills/okoddcat/gitflow/SKILL.md:122 | |
| MEDIUM | Shell command execution via recommended git alias The skill's documentation recommends adding a `git alias` to the user's `~/.gitconfig`. This alias contains shell commands (`git push`, `git remote get-url`, `echo`, `grep`, `sleep`, `gh run watch`, `glab ci status --live`). If an AI agent's execution environment automatically interprets and executes code blocks within markdown files, this could lead to arbitrary command execution on the host system. While the alias itself appears robust against argument injection, its direct execution by an agent constitutes command injection. Avoid recommending direct shell script configurations within skill documentation if the skill is intended for environments that automatically execute markdown code blocks. Instead, provide a dedicated tool or API for such functionality, or clearly separate user-facing documentation from agent-executable code. If shell execution is necessary, ensure robust input validation and least privilege. | LLM | SKILL.md:82 |
Scan History
Embed Code
[](https://skillshield.io/report/6ca91bfaf5ad3efb)
Powered by SkillShield