ClawAudit verdict

agentguard

security

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

GoPlus AgentGuard security framework for auditing installed skills, credentials, and network exposure; filesystem access is explicitly read-only for auditing purposes and the declared paths (`.ssh/`, `.gnupg/`) are stat-only checks, not key content reads, consistent with security auditing.

⚠ 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
90
transparency
80
maintenance

Permission integrity

Accesses agent memory/configuration files

agent_memory

Findings (24)

Pattern match critical

Pipe to bash — executes piped content as shell commands

SKILL.md · code · | Bash

Pattern match critical

Recursive delete from root or home — destructive command

SKILL.md · code · rm -rf /

Pattern match critical

Possible hardcoded credential

SKILL.md · code · credential: "A private key or API token was found in plain text in a file — it s

Pattern match high

Accesses .ssh directory

SKILL.md · frontmatter · .ssh/

Pattern match high

Pipe to sh — executes piped content as shell commands

SKILL.md · prose · downgraded · |sh

Pattern match high

Accesses sensitive system files

action-policies.md · prose · downgraded · /etc/passwd

Pattern match high

Pipe to python — executes piped content as Python code

scan-rules.md · prose · downgraded · | Python

Pattern match high

Uses eval() — can execute arbitrary code

scan-rules.md · prose · downgraded · eval(

Pattern match high

<script> tag in markdown — potential code injection

scripts/checkup-report.js · prose · downgraded · <script

Pattern match medium

References SSH/GPG private keys

SKILL.md · prose · downgraded · SSH_KEY

Pattern match medium

Accesses system credential store

evals.md · prose · downgraded · KEYCHAIN

Pattern match medium

Instructs covert action — may act without user awareness

SKILL.md · prose · downgraded · silently

Pattern match medium

Accesses cloud provider credentials

action-policies.md · prose · downgraded · ~/.aws

Pattern match medium

References sudo — requests elevated privileges

action-policies.md · prose · downgraded · sudo

Pattern match medium

Uses exec() — may execute shell commands

scan-rules.md · prose · downgraded · exec(

Pattern match medium

References child_process — can spawn system processes

scan-rules.md · prose · downgraded · child_process

Pattern match medium

Uses spawn() — can execute external programs

scan-rules.md · prose · downgraded · spawn(

Pattern match medium

os.system/popen — direct OS command execution

scan-rules.md · prose · downgraded · os.system(

Pattern match medium

Dynamic import() — loads module at runtime

scripts/auto-scan.js · prose · downgraded · import('

Pattern match low

Base64 encoding/decoding

SKILL.md · prose · downgraded · base64-encode

Pattern match low

References tunneling service

action-policies.md · prose · downgraded · ngrok

Pattern match low

pip3 install — installs Python packages at runtime

action-policies.md · prose · downgraded · pip3 install

Pattern match low

Popular HTTP library — network access

scan-rules.md · prose · downgraded · axios

Pattern match low

Python os.getenv — reads environment variable

scan-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.

network_inagent_memory

Is this flag fair?

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