Caveat verdict

intrusive-thoughts

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

Open-source autonomous agent behavior framework with mood systems and local memory; execution sinks (bash scripts, cron) are local and documented with optional integrations clearly disclosed.

⚠ 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
90
transparency
70
maintenance

Findings (8)

Pattern match high

subprocess execution — runs system commands from Python

SECURITY.md · code · subprocess.run(

Pattern match high

<script> tag in markdown — potential code injection

dashboard.py · prose · downgraded · <script>

Pattern match high

Pipe to python — executes piped content as Python code

intrusive.sh · prose · downgraded · | python3

Pattern match high

Uses eval() — can execute arbitrary code

SECURITY.md · prose · downgraded · eval(

Pattern match medium

References sudo — requests elevated privileges

docs/GETTING_STARTED.md · prose · downgraded · sudo

Pattern match medium

os.system/popen — direct OS command execution

SECURITY.md · prose · downgraded · os.system(

Pattern match low

Popular HTTP library — network access

night_journal.py · prose · downgraded · got

Pattern match low

Python os.environ.get — reads environment variable

stats.sh · prose · downgraded · os.environ.get(

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class B/C/D/F). 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