Caveat verdict

trustmyagent

trust-my-agent-ai

88
🟢 Trusted
No high-risk patterns surfaced by the deep scan — automated capability review, not behavioral proof.

Security posture monitoring running 41 read-only checks on the host and optionally reporting to a trust center dashboard; requires explicit user consent before any network transmission, open-source and transparent.

⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.

Automated static analysis — not a human review. Caveat flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.

0
security
100
transparency
90
maintenance

Findings (20)

Pattern match high

Accesses sensitive system files

checks/openclaw_checks.json · prose · downgraded · /etc/shadow

Pattern match high

Pipe to bash — executes piped content as shell commands

checks/openclaw_checks.json · prose · downgraded · |bash

Pattern match high

Pipe to python — executes piped content as Python code

checks/openclaw_checks.json · prose · downgraded · |python

Pattern match high

Recursive delete from root or home — destructive command

run.py · prose · downgraded · rm -rf /

Pattern match high

Pipe to sh — executes piped content as shell commands

run.py · prose · downgraded · |sh

Pattern match medium

References sudo — requests elevated privileges

SKILL.md · prose · downgraded · sudo

Pattern match medium

apt-get install — installs system packages

SKILL.md · prose · downgraded · apt-get install

Pattern match medium

apk add — installs Alpine packages

SKILL.md · prose · downgraded · apk add

Pattern match medium

setuid — privilege escalation mechanism

checks/openclaw_checks.json · prose · downgraded · setuid

Pattern match medium

Accesses shell history/config

checks/openclaw_checks.json · prose · downgraded · ~/.bash_history

Pattern match medium

subprocess execution — runs system commands from Python

run.py · prose · downgraded · subprocess.check_output(

Pattern match medium

Clears shell history — may hide tracks

run.py · prose · downgraded · history -c

Pattern match medium

Accesses .ssh directory

run.py · prose · downgraded · .ssh/

Pattern match medium

Accesses system credential store

run.py · prose · downgraded · keychain

Pattern match low

Sets world-executable permissions

checks/openclaw_checks.json · prose · downgraded · chmod 777

Pattern match low

Changes file ownership

checks/openclaw_checks.json · prose · downgraded · chown

Pattern match low

References tunneling service

checks/openclaw_checks.json · prose · downgraded · ngrok

Pattern match low

Python os.environ.get — reads environment variable

run.py · prose · downgraded · os.environ.get(

Pattern match low

Python urllib.request — network access

run.py · prose · downgraded · urllib.request

Pattern match low

References agent configuration files

run.py · prose · downgraded · agent_config

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class A/D). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.

Permissions & capabilities

Requires 1 system binary.

network_in

Is this flag fair?

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