ClawHub

Pull Request

Security checks across malware telemetry and agentic risk

Overview

This is an instruction-only pull request helper that mostly tells an agent how to make responsible, well-scoped PRs and avoid risky behavior.

Reasonable to install as a PR workflow guide. Before using it on unfamiliar repositories, review any test/build commands before running them, confirm the generated diff and PR text yourself, and avoid publishing prompts or session logs unless you have checked them for private information.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Tool MisuseTool Parameter Abuse, Chaining Abuse, Unsafe Defaults
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (5)

Autonomous Decision Making

Medium
Category
Excessive Agency
Content
### No Context
- PR appears out of nowhere for unsolicited feature
- No discussion, no approval, just code dump
- "I thought this would be cool" without checking if wanted

### Breaks CI Immediately
Confidence
75% confidence
Finding
no approval

Autonomous Decision Making

Medium
Category
Excessive Agency
Content
### No Context
- PR appears out of nowhere for unsolicited feature
- No discussion, no approval, just code dump
- "I thought this would be cool" without checking if wanted

### Breaks CI Immediately
- Tests fail on first push
Confidence
75% confidence
Finding
without checking

Autonomous Decision Making

Medium
Category
Excessive Agency
Content
### Drive-By Refactoring
- "Improved code quality" with no specifics
- Renamed variables "for clarity" without asking
- Reformatted unrelated code

### No AI Disclosure
Confidence
75% confidence
Finding
without asking

Unsafe Defaults

Medium
Category
Tool Misuse
Content
## Security

- [ ] **No secrets** — Not even "example" keys; use `<PLACEHOLDER>`
- [ ] **No unsafe patterns** — eval(), exec(), verify=False, debug=True
- [ ] **Input validation** — User input is sanitized

## AI-Assisted PR Requirements
Confidence
75% confidence
Finding
verify=False

Unsafe Defaults

Medium
Category
Tool Misuse
Content
## Security Red Flags

### Accidental Vulnerabilities
- `verify=False`, `debug=True`, `allow_all_origins`
- SQL string concatenation instead of parameterized queries
- `eval()`, `exec()`, `pickle.loads()` without safeguards
Confidence
75% confidence
Finding
verify=False

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal