ClawAudit verdict

tensorlake

tensorlake-skills

🟢 Trusted

Low risk — reviewed by ClawAudit, behavior matches stated purpose

Documents the Tensorlake SDK for sandboxed AI agent execution environments; all behaviors match the stated purpose of running isolated code sandboxes and fetching live docs.

⚠ 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.

security

transparency

maintenance

Findings (12)

Pattern match critical

Possible hardcoded credential

references/computer_use.md · code · password="tensorlake

Pattern match critical

Recursive delete from root or home — destructive command

references/sandbox_usecases.md · code · rm -rf /

Pattern match high

Pipe-to-shell pattern (curl | sh) — supply chain attack vector

SKILL.md · prose · downgraded · curl -fsSL https://tensorlake.ai/install | sh

Pattern match high

Pipe to sh — executes piped content as shell commands

SKILL.md · prose · downgraded · | sh

Pattern match high

Accesses .ssh directory

references/sandbox_sdk.md · code · .ssh/

Pattern match high

apt-get install — installs system packages

references/sandbox_sdk.md · code · apt-get install

Pattern match high

Pipe to python — executes piped content as Python code

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

Pattern match high

HTTP request to bare IP address — common in malicious payloads

references/sandbox_sdk.md · code · http://127.0.0.1

Pattern match medium

References agent configuration files

README.md · code · CLAUDE.md

Pattern match medium

References sudo — requests elevated privileges

references/sandbox_sdk.md · prose · downgraded · sudo

Pattern match low

Opens WebSocket connection

CHANGELOG.md · prose · downgraded · WebSocket

Pattern match low

Python directory traversal

references/sandbox_usecases.md · code · os.walk(

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class A/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.

Is this flag fair?

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