ClawAudit verdict

cursor-agent

cursor-cloud-agent

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

Manages Cursor Cloud Agents via the official api.cursor.com API using a user-provided API key stored locally; all operations are through the official documented API for cloud coding tasks.

⚠ 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.

35
security
40
transparency
70
maintenance

Findings (5)

Pattern match critical

Possible hardcoded credential

references/get-token.md · code · API_KEY='your_api_key_here

Pattern match high

Accesses shell history/config

references/get-token.md · code · ~/.zshrc

Pattern match medium

subprocess execution — runs system commands from Python

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

Pattern match low

Python urllib.request — network access

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

Pattern match low

Python os.environ.get — reads environment variable

scripts/cursor_bga.py · prose · downgraded · os.environ.get(

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.

credential_access

Is this flag fair?

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