ClawHub

pr-review-expert

Security checks across malware telemetry and agentic risk

Overview

This is an instruction-only pull request review helper with visible, purpose-aligned commands, though users should be careful with repository and ticket-system credentials.

Install if you want a structured PR/MR review checklist and are comfortable with commands that may read private repository data, save diffs temporarily, run project tests, and optionally query Jira or Linear. Use scoped tokens, avoid running test commands from untrusted branches outside a sandbox, and skip or manually perform ticket checks when external disclosure of internal ticket IDs is not approved.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (3)

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The skill instructs users to send PR-linked ticket identifiers and related metadata to third-party services (Jira and Linear) using authenticated API calls, but it does not warn that repository context, ticket references, and potentially sensitive workflow metadata will be transmitted externally. In a PR review skill, this is more dangerous because users may run the commands against internal projects and assume all processing is local, creating an avoidable data disclosure and compliance risk.

External Transmission

Medium
Category
Data Exfiltration
Content
# Linear ticket
LINEAR_ID="abc-123"
curl -s -H "Authorization: $LINEAR_API_KEY" \
  -H "Content-Type: application/json" \
  --data "{\"query\": \"{ issue(id: \\\"$LINEAR_ID\\\") { title state { name } } }\"}" \
  https://api.linear.app/graphql | jq .
Confidence
90% confidence
Finding
curl -s -H "Authorization: $LINEAR_API_KEY" \ -H "Content-Type: application/json" \ --data

External Transmission

Medium
Category
Data Exfiltration
Content
curl -s -H "Authorization: $LINEAR_API_KEY" \
  -H "Content-Type: application/json" \
  --data "{\"query\": \"{ issue(id: \\\"$LINEAR_ID\\\") { title state { name } } }\"}" \
  https://api.linear.app/graphql | jq .
```

---
Confidence
87% confidence
Finding
https://api.linear.app/

VirusTotal

54/54 vendors flagged this skill as clean.

View on VirusTotal