Caveat verdict

research-supervisor-pro

eve-research-supervisor-pro

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

This skill manages a research lifecycle by reading/writing local session memory files and querying academic APIs; it explicitly prohibits hallucinating results and the truncated content shows only local file operations and user-facing onboarding flows.

⚠ 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
100
maintenance

Permission integrity

Performs file operations but does not declare file-accessing binaries

file_read

Installs packages at runtime — transitive dependencies are not auditable

package_install

Findings (9)

Pattern match high

Instructs covert action — may act without user awareness

SKILL.md · code · silently

Pattern match high

Possible hardcoded credential

config.yaml · prose · downgraded · api_key: "${OPENAI_API_KEY:-}

Pattern match medium

References sudo — requests elevated privileges

install.sh · prose · downgraded · sudo

Pattern match medium

subprocess execution — runs system commands from Python

scripts/experiment_alert.py · prose · downgraded · subprocess.run(

Pattern match medium

References SSH/GPG private keys

scripts/experiment_alert.py · prose · downgraded · ssh_key

Pattern match medium

Accesses .ssh directory

scripts/server_monitor.py · prose · downgraded · .ssh/

Pattern match low

References agent memory files

SKILL.md · prose · downgraded · memory.md

Pattern match low

pip3 install — installs Python packages at runtime

install.sh · prose · downgraded · pip3 install

Pattern match low

Python os.environ.get — reads environment variable

scripts/build_survey.py · prose · downgraded · os.environ.get(

Why the tier is capped

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

file_readpackage_installnetwork_in

Is this flag fair?

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