ClawAudit verdict

openclaw-upgrade-assistant

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

The content appears to be an upgrade assistant, analyzing OpenClaw version updates and generating compatibility reports. It seems to provide legitimate backup and assessment functionality.

⚠ 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.

50
security
90
transparency
80
maintenance

Findings (10)

Pattern match high

Uses exec() — may execute shell commands

SKILL.md · code · exec(

Pattern match medium

Popular HTTP library — network access

node_modules/node-fetch/README.md · code · node-fetch

Pattern match low

Accesses sensitive environment variables

index.js · prose · downgraded · process.env.GITHUB_TOKEN

Pattern match low

References agent memory files

index.js · prose · downgraded · MEMORY.md

Pattern match low

process.nextTick — defers execution to next tick

node_modules/graceful-fs/legacy-streams.js · prose · downgraded · process.nextTick(

Pattern match low

Changes file ownership

node_modules/graceful-fs/polyfills.js · prose · downgraded · chown

Pattern match low

Blob URL — may embed executable content

node_modules/node-fetch/lib/index.es.js · prose · downgraded · blob:

Pattern match low

Node http/https module — low-level network access

node_modules/node-fetch/lib/index.js · prose · downgraded · require('http')

Pattern match low

Uses XMLHttpRequest — network access

node_modules/node-fetch/README.md · prose · downgraded · XMLHttpRequest

Pattern match low

Makes HTTP request to external URL

node_modules/node-fetch/README.md · code · fetch('https://

Permissions & capabilities

No declared permissions — minimal attack surface.

process_exec

Is this flag fair?

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