ClawAudit verdict

test0413-6348

🟢 Trusted

Low risk — reviewed by ClawAudit, behavior matches stated purpose

A security audit tool performing static analysis and maintaining append-only local logs; all operations are local and it explicitly does not execute audited skill code.

⚠ 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

100

transparency

maintenance

Findings (21)

Pattern match high

Pipe to bash — executes piped content as shell commands

config/risk-rules.json · prose · downgraded · | bash

Pattern match high

Pipe to sh — executes piped content as shell commands

config/risk-rules.json · prose · downgraded · | sh

Pattern match high

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

config/risk-rules.json · prose · downgraded · curl | sh

Pattern match high

Pipe-to-shell pattern (wget | sh)

config/risk-rules.json · prose · downgraded · wget | sh

Pattern match high

Recursive delete from root or home — destructive command

config/risk-rules.json · prose · downgraded · rm -rf /

Pattern match high

Bash /dev/tcp — raw TCP connection via shell

config/risk-rules.json · prose · downgraded · /dev/tcp/

Pattern match high

Accesses sensitive system files

config/risk-rules.json · prose · downgraded · /etc/shadow

Pattern match high

Uses eval() — can execute arbitrary code

config/semantic-patterns.json · prose · downgraded · eval(

Pattern match medium

subprocess execution — runs system commands from Python

config/risk-rules.json · prose · downgraded · subprocess.call(

Pattern match medium

References child_process — can spawn system processes

config/risk-rules.json · prose · downgraded · child_process

Pattern match medium

os.system/popen — direct OS command execution

config/risk-rules.json · prose · downgraded · os.system(

Pattern match medium

setuid — privilege escalation mechanism

config/risk-rules.json · prose · downgraded · setuid

Pattern match medium

Raw socket connection — low-level network access

config/risk-rules.json · prose · downgraded · socket.connect(

Pattern match medium

Uses exec() — may execute shell commands

config/semantic-patterns.json · prose · downgraded · exec(

Pattern match medium

Accesses cloud provider credentials

config/semantic-patterns.json · prose · downgraded · ~/.aws

Pattern match medium

subprocess with shell=True — command injection vector

scripts/skills_audit.py · prose · downgraded · subprocess.run(argv", "subprocess.run(argv,", "subprocess.run(["

Pattern match low

Sets world-executable permissions

config/risk-rules.json · prose · downgraded · chmod 777

Pattern match low

Python urllib.request — network access

config/risk-rules.json · prose · downgraded · urllib.request

Pattern match low

Popular HTTP library — network access

config/risk-rules.json · prose · downgraded · axios

Pattern match low

pip3 install — installs Python packages at runtime

config/risk-rules.json · prose · downgraded · pip3 install

Pattern match low

Python shutil file operation — copies/moves/deletes files

scripts/skills_audit.py · prose · downgraded · shutil.rmtree(

Why the tier is capped

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