Skillv1.0.0

ClawScan security

Portfolio Watcher Hardened · ClawHub's context-aware review of the artifact, metadata, and declared behavior.

BenignApr 29, 2026, 1:42 AM

Verdict: benign
Confidence: high
Model: gpt-5-mini
Summary: This instruction-only skill is internally coherent with its stated purpose (portfolio monitoring and alerts) and does not request extraneous credentials, installs, or system access.
Guidance: This skill appears coherent and relatively low-risk because it's instruction-only and requests no credentials or installs. Before installing, confirm two things with the skill author or operator: (1) Where does the skill fetch market prices from (which public APIs or services) and whether that requires any credentials or has usage limits? (2) How and where does it persist your holdings/alerts (local ephemeral memory, platform storage, or external storage)? Also verify how alerts are delivered (in-app messages, email, SMS, webhook) and whether delivering alerts would require you to provide any external tokens. Note the SAFETY.md shows thoughtful guardrails (privacy, accuracy labeling, explicit confirmation for destructive actions) — that's good. If you plan to use it with real money decisions, do not rely on its figures as exact; verify with your brokerage for trading or tax decisions.

Purpose & Capability: okName/description (monitor holdings, set alerts, track performance) align with the SKILL.md instructions. The skill is instruction-only and does not declare any unrelated environment variables, binaries, or config paths that would be disproportionate to a portfolio tracker.
Instruction Scope: okSKILL.md confines actions to adding/updating holdings, checking prices, setting alerts, and computing performance. It includes explicit guardrails around accuracy, privacy, and confirmation for destructive actions. The instructions do not ask to read unrelated system files or to exfiltrate data to unknown endpoints.
Install Mechanism: okNo install spec and no code files are included (instruction-only). Nothing is written to disk or downloaded as part of the skill itself, which minimizes install risk.
Credentials: okThe skill declares no required environment variables, credentials, or config paths. That is proportionate to the described functionality (the SKILL.md implies use of platform messaging and public market data rather than external private APIs).
Persistence & Privilege: okalways is false; normal autonomous invocation is allowed. The skill does not request elevated or permanent system presence nor does it modify other skills' configs. The SKILL.md requires explicit confirmation for destructive operations, which mitigates accidental data loss.