Caveat verdict

smart-agent-template

🟢 Trusted

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

Agent workflow template providing task classification and context management methodology, references a public GitHub repo for setup — no sensitive data access or external transmission.

⚠ 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.

security

transparency

maintenance

Findings (15)

Pattern match critical

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

docs/OLLAMA_SETUP.md · code · curl -fsSL https://ollama.com/install.sh | sh

Pattern match critical

Pipe to sh — executes piped content as shell commands

docs/OLLAMA_SETUP.md · code · | sh

Pattern match critical

Possible hardcoded credential

docs/OLLAMA_SETUP.md · code · TOKEN="你的Bot Token

Pattern match critical

Recursive delete from root or home — destructive command

docs/OLLAMA_SETUP.md · code · rm -rf ~

Pattern match high

HTTP request to bare IP address — common in malicious payloads

docs/FEISHU_INTEGRATION.md · code · http://127.0.0.1

Pattern match high

References sudo — requests elevated privileges

integrations/feishu/DEPLOYMENT.md · code · sudo

Pattern match high

Uses exec() — may execute shell commands

process-standards/core/SECURITY_CHECK.md · code · exec(

Pattern match medium

Python os.getenv — reads environment variable

CHROMADB_INTEGRATION.md · code · os.getenv(

Pattern match medium

References agent memory files

CHROMADB_INTEGRATION.md · code · memory.md

Pattern match medium

References tunneling service

docs/FEISHU_INTEGRATION.md · code · ngrok

Pattern match medium

pip3 install — installs Python packages at runtime

integrations/feishu/DEPLOYMENT.md · code · pip3 install

Pattern match medium

Opens WebSocket connection

integrations/feishu/DEPLOYMENT.md · code · WebSocket

Pattern match medium

subprocess execution — runs system commands from Python

integrations/memory_manager.py · prose · downgraded · subprocess.run(

Pattern match low

Python urllib.request — network access

integrations/feishu/bot_longconn.py · prose · downgraded · urllib.request

Pattern match low

References agent configuration files

README.md · prose · downgraded · CLAUDE.md

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.

Is this flag fair?

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