ClawHub

Tarot Reading

v1.2.0

A tarot reading and interpretation tool, part of the fortune-telling-skills suite. Based on the Rider-Waite-Smith system, it supports upright and reversed re...

⭐ 0· 228·1 current·1 all-time
byeamanc@eamanc-lab
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
✓
Purpose & Capability
The name/description (tarot reading) matches the runtime instructions and the included reference files. There are no unrelated binaries, cloud credentials, or system-wide config requirements that would be out of scope for a tarot interpreter.
ℹ
Instruction Scope
Instructions are limited to parsing user intent, randomly drawing cards from the included 78-card references, interpreting them with LLM output, and optionally reading/writing this skill's MEMORY.md (and a same-repo fortune-hub/MEMORY.md if present). Reading/writing those repo-local memory files is within scope for personalization but users should be aware those files may contain stored preferences or other data.
✓
Install Mechanism
No install spec and no code files — instruction-only — so nothing is downloaded or written to disk by an installer. This is the lowest-risk install model.
✓
Credentials
The skill requests no environment variables, credentials, or external config paths. Its only data access is to the provided reference files and optional repo-local MEMORY.md files, which is proportional to the described functionality.
✓
Persistence & Privilege
always:false and no elevated privileges. The skill may read/write its own MEMORY.md only when instructed; that scoped memory access is reasonable for storing user preferences and is explicitly gated by the instructions.
Assessment
This skill is instruction-only and appears coherent with its tarot purpose. Before installing, review the repo-local MEMORY.md (if present) to see what, if any, user preferences or data would be read or stored. If you do not want any persistent memory written, decline or remove MEMORY.md write permissions. Although there are no external endpoints or credentials requested, you may wish to verify the homepage repository (https://github.com/eamanc-lab/fortune-telling-skills) if you want source-level assurance. If you expect the agent to run autonomously, remember it could produce readings without prompting but it does not have network/credential access from this skill alone.

Like a lobster shell, security has layers — review code before you run it.

latestvk9720x4nap72qw6wt15aj8tdjs83ceps

License

MIT-0
Free to use, modify, and redistribute. No attribution required.
Termshttps://spdx.org/licenses/MIT-0.html

Comments