Caveat verdict
smart-agent-workflow
Agent workflow methodology for task management and context optimization, purely instructional with no network calls or credential access.
⚠ 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.
Findings (8)
Pipe-to-shell pattern (curl | sh) — supply chain attack vector
docs/OLLAMA_SETUP.md · code · curl -fsSL https://ollama.com/install.sh | sh
Pipe to sh — executes piped content as shell commands
docs/OLLAMA_SETUP.md · code · | sh
Possible hardcoded credential
docs/OLLAMA_SETUP.md · code · TOKEN="你的Bot Token
Recursive delete from root or home — destructive command
docs/OLLAMA_SETUP.md · code · rm -rf ~
HTTP request to bare IP address — common in malicious payloads
docs/OLLAMA_SETUP.md · code · http://127.0.0.1
Uses exec() — may execute shell commands
process-standards/core/SECURITY_CHECK.md · code · exec(
References agent configuration files
SKILL.md · code · CLAUDE.md
References agent memory files
process-standards/core/CONTEXT_MANAGEMENT_v2.0.md · code · MEMORY.md
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class A/B). 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?
Thanks — recorded.