ClawAudit verdict

skill-sec-scan

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

A security scanning tool that performs static analysis via a local scan.sh script and follows a user-confirmation workflow before generating LLM prompts; no data exfiltration is present.

⚠ 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
70
transparency
80
maintenance

Findings (18)

Pattern match critical

Pipe to python — executes piped content as Python code

SKILL.md · code · | Python

Pattern match critical

Pipe to sh — executes piped content as shell commands

references/dangerous-commands.md · code · |sh

Pattern match high

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

references/dangerous-commands.md · prose · downgraded · curl \| bash

Pattern match high

Pipe-to-shell pattern (wget | sh)

references/dangerous-commands.md · prose · downgraded · wget -O- \| sh

Pattern match high

Recursive delete from root or home — destructive command

references/dangerous-commands.md · prose · downgraded · rm -rf /

Pattern match high

Pipe to bash — executes piped content as shell commands

references/dangerous-commands.md · prose · downgraded · | bash

Pattern match high

Uses eval() — can execute arbitrary code

references/dangerous-commands.md · prose · downgraded · eval(

Pattern match high

References sudo — requests elevated privileges

references/dangerous-commands.md · code · sudo

Pattern match high

Accesses sensitive system files

references/dangerous-commands.md · prose · downgraded · /etc/passwd

Pattern match medium

References child_process — can spawn system processes

index.js · prose · downgraded · child_process

Pattern match medium

Uses exec() — may execute shell commands

references/dangerous-commands.md · prose · downgraded · exec(

Pattern match medium

os.system/popen — direct OS command execution

references/dangerous-commands.md · prose · downgraded · os.system(

Pattern match medium

Accesses .ssh directory

references/dangerous-commands.md · prose · downgraded · .ssh/

Pattern match medium

Popular HTTP library — network access

references/dangerous-commands.md · code · axios

Pattern match low

Opens WebSocket connection

node/scanner.js · prose · downgraded · WebSocket

Pattern match low

Sets world-executable permissions

references/dangerous-commands.md · prose · downgraded · chmod 777

Pattern match low

Python urllib.request — network access

references/rules.md · prose · downgraded · urllib.request

Pattern match low

Python os.getenv — reads environment variable

references/rules.md · prose · downgraded · os.getenv(

Why the tier is capped

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

data_encoding

Is this flag fair?

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