Back to skill
Skillv1.0.0
ClawScan security
Fear and Greed Index · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignFeb 25, 2026, 4:09 AM
- Verdict
- benign
- Confidence
- high
- Model
- gpt-5-mini
- Summary
- The skill is an instruction-only wrapper for a public Alternative.me API endpoint and does not request credentials, install software, or perform unrelated actions.
- Guidance
- This skill is low-risk: it only queries a public API and does not ask for secrets or install software. Before installing, confirm you trust the skill owner (source metadata is unknown) and that your agent environment permits outbound network calls to that API. Also consider rate limits and caching so repeated automated calls don't hit the public endpoint excessively. If you require stricter controls, restrict the agent's network access or run the query manually.
Review Dimensions
- Purpose & Capability
- okThe name/description (fetching the Fear & Greed Index) matches the instructions, which simply call the public Alternative.me API. No unrelated capabilities or requirements are declared.
- Instruction Scope
- okSKILL.md instructs a single network fetch (curl to https://api.alternative.me/fng/?limit=1) and explains how to interpret the returned JSON. It does not direct reading local files, accessing environment variables, or transmitting user data to other endpoints.
- Install Mechanism
- okNo install spec or code files are present (instruction-only). Nothing is downloaded or written to disk by the skill itself.
- Credentials
- okNo environment variables, credentials, or config paths are requested. This is proportional to the stated purpose (public API access requires no auth).
- Persistence & Privilege
- okalways is false and there are no indications the skill requests elevated or persistent privileges. Autonomous invocation of the skill is allowed by default, which is expected for skills of this type.