Caveat verdict

investorclaw

🟢 Trusted

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

Portfolio analyzer skill operating via a local MCP-HTTP endpoint; enforces strict data-integrity rules requiring all figures to come from HMAC-signed tool results, which is responsible behavior for a financial tool.

⚠ 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

Permission integrity

Makes network requests but does not declare curl/wget in required binaries

network_out

Findings (15)

Pattern match critical

Pipe-to-python pattern — remote code execution risk

SKILL.md · code · curl -sS http://127.0.0.1:18090/api/portfolio/tools | python

Pattern match critical

Pipe to python — executes piped content as Python code

SKILL.md · code · | python3

Pattern match critical

Recursive delete from root or home — destructive command

agent-skills/claude-code/INSTALL.md · code · rm -rf ~

Pattern match critical

Possible hardcoded credential

docs/GETTING_STARTED_MASSIVE.md · code · API_KEY="$MASSIVE_API_KEY

Pattern match high

HTTP request to bare IP address — common in malicious payloads

SKILL.md · code · http://127.0.0.1

Pattern match high

Writes to SKILL.md — self-modifying skill

agent-skills/claude-code/INSTALL.md · prose · downgraded · SKILL.md + an MCP-server config write

Pattern match medium

References sudo — requests elevated privileges

SKILL.md · prose · downgraded · sudo

Pattern match medium

Accesses OpenClaw config/secrets directly

agent-skills/openclaw/INSTALL.md · prose · downgraded · ~/.openclaw/openclaw.json

Pattern match medium

Instructs covert action — may act without user awareness

agent-skills/zeroclaw/INSTALL.md · prose · downgraded · silently

Pattern match medium

Social engineering — falsely claims user authorization

DISCLAIMER.md · prose · downgraded · the user has configured

Pattern match low

Popular HTTP library — network access

bridge/investorclaw_bridge/bundle_schema.py · prose · downgraded · Got

Pattern match low

Python shutil file operation — copies/moves/deletes files

bridge/investorclaw_bridge/bundle.py · prose · downgraded · shutil.move(

Pattern match low

Python os.environ.get — reads environment variable

bridge/investorclaw_bridge/dashboard.py · prose · downgraded · os.environ.get(

Pattern match low

References agent configuration files

install.yaml · prose · downgraded · agent_config

Pattern match low

References agent memory files

RFC-v0.1.md · prose · downgraded · MEMORY.md

Why the tier is capped

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

network_outnetwork_in

Is this flag fair?

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