Caveat verdict

Li_codeql_LLM

li-codeql-llm

88
🟢 Trusted
No high-risk patterns surfaced by the deep scan — automated capability review, not behavioral proof.

Reads local files AND makes external network calls

CodeQL static analysis skill that runs local scans and produces SARIF reports; the LLM analysis is performed in-context using local scan results, all operations are legitimate security audit workflows with no external exfiltration of code or credentials.

Automated static analysis — not a human review. Caveat flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.

0
security
60
transparency
70
maintenance

What it does

These are capability combinations: each listed behavior occurs in the skill, but Caveat detects co-occurrence — it does not verify that one flows into another. Read the code to confirm a live chain.

Capability combination critical

Reads local files AND makes external network calls — the capabilities for data exfiltration co-occur (data-flow not verified)

LLM02 · LLM06 · ASI03

Permission integrity

Makes network requests but does not declare curl/wget in required binaries

network_out

Performs file operations but does not declare file-accessing binaries

file_read

Installs packages at runtime — transitive dependencies are not auditable

package_install

Findings (12)

Pattern match critical

Dynamic __import__('os') — Python OS command execution

IMPLEMENTATION.md · code · __import__('os')

Pattern match critical

Accesses sensitive system files

IMPLEMENTATION.md · code · /etc/passwd

Pattern match critical

Uses eval() — can execute arbitrary code

CodeQL+OpenClaw_LLM集成方案.md · code · eval(

Pattern match critical

Pipe-to-python pattern — remote code execution risk

JENKINS_MANUAL_SETUP.md · code · curl -u devops:devsecops http://localhost:8080/api/json | python

Pattern match critical

Pipe to python — executes piped content as Python code

JENKINS_MANUAL_SETUP.md · code · | python3

Pattern match critical

Possible hardcoded credential

Jenkins_Pipeline_修复报告.md · code · password='password1

Pattern match high

subprocess execution — runs system commands from Python

IMPLEMENTATION.md · code · subprocess.run(

Pattern match high

<script> tag in markdown — potential code injection

create_jenkins_job.py · prose · downgraded · <script>

Pattern match high

HTTP request to bare IP address — common in malicious payloads

Jenkins_Pipeline_更新完成报告.md · code · http://192.168.4.53

Pattern match high

References sudo — requests elevated privileges

JENKINS_SETUP.md · code · sudo

Pattern match high

Uses exec() — may execute shell commands

一键使用说明.md · code · exec(

Pattern match low

Python os.environ.get — reads environment variable

codeql_llm_scan.py · prose · downgraded · os.environ.get(

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class B/D/F). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.

Permissions & capabilities

No declared permissions — minimal attack surface.

network_outfile_readpackage_install
Check another skill Browse the registry Auditing your own skills or configs? Use the API