Skill flagged — suspicious patterns detected
ClawHub Security flagged this skill as suspicious. Review the scan results before using.
Agent Reputation Tracker
v1.1.0Track and display your agent's betting reputation. Computes win rate, ROI, volume, streaks, max drawdown, and Sharpe proxy from local bet history. Formats ou...
⭐ 0· 72·0 current·0 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Suspicious
medium confidencePurpose & Capability
Name/description align with the code in SKILL.md: it computes betting metrics and formats reputation cards. Required binaries (python3, sqlite3) are appropriate. One minor inconsistency: the runtime expects a specific local DB path (~/.openclaw/data/bet_log.db) but the registry metadata did not declare any required config paths.
Instruction Scope
Instructions explicitly run Python one-liners that open and query a local SQLite DB at ~/.openclaw/data/bet_log.db and (if absent) offer to create it. This stays within the skill's purpose but involves reading potentially sensitive personal data (full bet history) and generating payloads for external publication. The SKILL.md also references creating Moltbook profile JSON and (implicitly) publishing it — see environment proportionality.
Install Mechanism
No install spec and no code files — the skill is instruction-only, which means nothing is downloaded or written by an installer. Risk from installation is minimal.
Credentials
The skill does not require any environment variables to run. SKILL.md declares an optional Moltbook API key (MOLTBOOK_API_KEY) for publishing profiles; this is proportionate to the 'publish to Moltbook' feature but is a data-exfiltration vector if supplied. The registry summary showed no required envs — the Moltbook key in SKILL.md is optional, but supplying it grants outgoing write capability to an external service.
Persistence & Privilege
always:false (good). Default platform behavior allows autonomous invocation; combined with the skill's ability to read local bet history and publish to Moltbook (if an API key is present), this increases privacy/exfiltration risk if you allow the agent to invoke skills without oversight. The skill does not request system-wide config changes or other skills' credentials.
What to consider before installing
This skill appears to do what it claims, but it reads a local betting database (~/.openclaw/data/bet_log.db) and can produce payloads for an external service (Moltbook) if you provide MOLTBOOK_API_KEY. Before installing or enabling: 1) Confirm where your betting DB lives and whether you want that data read; the skill assumes ~/.openclaw/data/bet_log.db — move or restrict that file if needed. 2) Do not set MOLTBOOK_API_KEY unless you explicitly want the skill to publish your agent profile externally. 3) If you allow autonomous invocation, consider restricting or monitoring skill actions (or keep the API key unset) to prevent automatic publishing. 4) If you want extra assurance, open the SKILL.md locally and review the Python snippets; they are short and readable and you can run them manually to preview outputs before giving the agent permission to run them automatically.Like a lobster shell, security has layers — review code before you run it.
agentbetsvk97d1h7vps078f46zb694a670583jx0gbettingvk97d1h7vps078f46zb694a670583jx0glatestvk97d1h7vps078f46zb694a670583jx0gopenclawvk97d1h7vps078f46zb694a670583jx0gprediction-marketsvk97d1h7vps078f46zb694a670583jx0gsports-bettingvk97d1h7vps078f46zb694a670583jx0g
License
MIT-0
Free to use, modify, and redistribute. No attribution required.
Runtime requirements
🏆 Clawdis
Binspython3, sqlite3