- prevent-direct-push.json 16 lines · 553 B
Scanned by
NVIDIA SkillSpector
Automated static analysis (no LLM) · v2.12.0 · 2026-11-19
3 observations in 3 categories
- Dangerous Code Execution 1
- MCP Least Privilege 1
- Tool Misuse 1
SkillSpector looks for patterns such as shell commands, credential access, network calls or unpinned dependencies. An observation is something worth reading in the files before you install, not a confirmed vulnerability. Components that run code locally, like hooks, MCP servers and security tooling, naturally show more of them. Open one to see the lines it points at.
Tool Parameter AbuseTool Misuse · prevent-direct-push.py:16
| 14 | command = tool_input.get("command", "") |
| 15 | |
| 16 | # Only validate git push commands |
| 17 | if tool_name != "Bash" or "git push" not in command: |
| 18 | sys.exit(0) |
Without declared permissions the skill's intent is opaque and cannot be validated.MCP Least Privilege · SKILL.md:1
No code excerpt: this observation is about the component as a whole, not one line.
subprocess module callDangerous Code Execution · prevent-direct-push.py:22
| 20 | # Get current branch |
| 21 | try: |
| 22 | current_branch = subprocess.check_output( |
| 23 | ["git", "branch", "--show-current"], |
| 24 | stderr=subprocess.DEVNULL, |
Learn more about NVIDIA SkillSpector or how components are reviewed.