ClawHub
Back to skill

Security audit

MergeIQ: Automatically Score & Prioritise PR Complexity for GitLab and GitHub

Security checks for vulnerabilities and agentic risk

Overview

This skill is a local PR/MR complexity scorer; its GitHub and GitLab examples are user-directed metadata fetches, not hidden execution or exfiltration.

Install only if you are comfortable using it with PR/MR metadata from the repositories you choose. For private repos, use least-privilege GitHub or GitLab tokens, avoid processing sensitive review data unless approved, and prefer saved JSON input when you want tighter control over what is analyzed.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (8)

External Script Fetching

High
Category
Supply Chain
Confidence
90% confidence
Finding

Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.

Content

Scanner excerpt · SKILL.md (reported line 49)May include surrounding context.

md
| python score_mr.py --provider github

# Score a GitLab MR (with diff stats)
curl -s "https://gitlab.com/api/v4/projects/PROJECT_ID/merge_requests/IID?include_diff_stats=true" \
     -H "PRIVATE-TOKEN: $GITLAB_TOKEN" \
     | python score_mr.py --provider gitlab

External Script Fetching

High
Category
Supply Chain
Confidence
90% confidence
Finding

Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.

Content

Scanner excerpt · score_mr.py (reported line 7)May include surrounding context.

python
Usage:
    # Score a GitLab MR (pipe in JSON from GitLab API)
    curl -s "https://gitlab.com/api/v4/projects/:id/merge_requests/:iid?include_diff_stats=true" \
         -H "PRIVATE-TOKEN: $GITLAB_TOKEN" | python score_mr.py --provider gitlab

    # Score a GitHub PR

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
91% confidence
Finding

The skill includes shell-based usage examples that invoke networked commands and process their output, but it declares no explicit tool scope or permissions. In an agent environment, missing scope metadata can allow broader-than-expected command execution or network use, making the skill harder to sandbox safely.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 44)May include surrounding context.

md
-H "PRIVATE-TOKEN: $GITLAB_TOKEN" | python score_mr.py --provider gitlab

    # Score a GitHub PR
    curl -s "https://api.github.com/repos/:owner/:repo/pulls/:number" \
         -H "Authorization: Bearer $GITHUB_TOKEN" | python score_mr.py --provider github

    # Score with enriched data (file paths, reviews)

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · score_mr.py (reported line 11)May include surrounding context.

python
-H "PRIVATE-TOKEN: $GITLAB_TOKEN" | python score_mr.py --provider gitlab

    # Score a GitHub PR
    curl -s "https://api.github.com/repos/:owner/:repo/pulls/:number" \
         -H "Authorization: Bearer $GITHUB_TOKEN" | python score_mr.py --provider github

    # Score with enriched data (file paths, reviews)

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
92% confidence
Finding

The README instructs users to send authenticated GitHub/GitLab PR and MR metadata to external APIs but does not warn that repository metadata, comments, file names, and review data may be sensitive. This can lead users to expose private project information or tokens without realizing the privacy and compliance implications.

Content

No source excerpt is available for this finding.

External Script Fetching

Low
Category
Supply Chain
Confidence
15% confidence
Finding

Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.

Content

Scanner excerpt · SKILL.md (reported line 44)May include surrounding context.

bash
# Score a GitHub PR (basic — just the PR object)
curl -s "https://api.github.com/repos/OWNER/REPO/pulls/NUMBER" \
     -H "Authorization: Bearer $GITHUB_TOKEN" \
     | python score_mr.py --provider github

External Script Fetching

Low
Category
Supply Chain
Confidence
15% confidence
Finding

Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.

Content

Scanner excerpt · score_mr.py (reported line 11)May include surrounding context.

python
-H "PRIVATE-TOKEN: $GITLAB_TOKEN" | python score_mr.py --provider gitlab

    # Score a GitHub PR
    curl -s "https://api.github.com/repos/:owner/:repo/pulls/:number" \
         -H "Authorization: Bearer $GITHUB_TOKEN" | python score_mr.py --provider github

    # Score with enriched data (file paths, reviews)

Static analysis

No suspicious patterns detected.