Back to skill
Skillv1.0.0
ClawScan security
Daily Horoscope · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignMar 6, 2026, 6:29 AM
- Verdict
- benign
- Confidence
- high
- Model
- gpt-5-mini
- Summary
- The skill's code and instructions match its horoscope purpose, require only python3, perform local calculations, and do not request credentials or network access.
- Guidance
- This skill is internally consistent and runs a local Python script to produce horoscope output. It requests no secrets and makes no network calls. If you plan to install: ensure python3 is available in the environment, and review the script if you need a more accurate lunar/calendar implementation (the code uses a simplified day-offset method and simplified lunar month mapping). If you will allow autonomous invocation, note the skill runs only local calculations — still consider running it in a restricted environment if you want to limit execution of arbitrary scripts.
Review Dimensions
- Purpose & Capability
- okName/description (每日宜忌) align with the included Python script and SKILL.md. The only required binary is python3, which is appropriate for running horoscope.py. No unrelated credentials, binaries, or config paths are requested.
- Instruction Scope
- okSKILL.md instructs the agent to run the included horoscope.py with 'today' or 'tomorrow'. The script performs local date/ganzhi calculations and prints results. It does not read arbitrary files, environment variables, or send data to external endpoints.
- Install Mechanism
- okNo install spec — instruction-only plus a single Python file. No downloads or external package installs are performed by the skill.
- Credentials
- okThe skill requires no environment variables, credentials, or configuration paths. That is proportionate for a local horoscope generator.
- Persistence & Privilege
- okalways is false and the skill does not attempt to modify agent/system configuration or other skills. It has normal, limited runtime scope.