ClawAudit verdict

drawio-skill

drawio-pro-skill

88
🟢 Trusted
Low risk — reviewed by ClawAudit, behavior matches stated purpose

Generates draw.io XML and exports diagrams via the local draw.io desktop CLI; network access is limited to optional CDN logo fetching for AI brand icons, matching the stated diagramming purpose.

⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.

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

0
security
100
transparency
90
maintenance

Permission integrity

Installs packages at runtime — transitive dependencies are not auditable

package_install

Findings (8)

Pattern match high

Downloads executables from external URLs

SKILL.md · code · install from https://

Pattern match high

References sudo — requests elevated privileges

references/autolayout.md · code · sudo

Pattern match high

Pipe to python — executes piped content as Python code

references/autolayout.md · prose · downgraded · | Python

Pattern match high

Writes to SKILL.md — self-modifying skill

references/style-presets.md · prose · downgraded · SKILL.md. If the flow between two shapes matches a token from `preset.edges.dash

Pattern match medium

Instructs covert action — may act without user awareness

SKILL.md · prose · downgraded · silently

Pattern match medium

subprocess execution — runs system commands from Python

scripts/autolayout.py · prose · downgraded · subprocess.run(

Pattern match medium

Dynamic import() — loads module at runtime

scripts/jsimports.py · prose · downgraded · import("

Pattern match low

Python urllib.request — network access

scripts/aiicons.py · prose · downgraded · urllib.request

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class D). 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.

package_installnetwork_indata_encoding

Is this flag fair?

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