Tarot from Univoice
v1.0.0A reflective tarot draw for emotional support (presence-first, non-clinical, non-predictive).
⭐ 2· 784·31 current·32 all-time
byShiraz@yangsenessa
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name/description match the SKILL.md: a reflective tarot draw. The skill requires no binaries, env vars, or installs and does not ask for unrelated capabilities. All declared requirements are proportional to a text-only tarot helper.
Instruction Scope
Instructions are narrowly scoped to prompting, internal random selection of cards, and producing reflections. The only safety-related instruction is to pause the reading and shift to 'safety-first support' if the user expresses explicit self-harm intent; the SKILL.md does not define the safety protocol itself, so proper handling depends on the host agent's crisis/safety mechanisms.
Install Mechanism
No install spec and no code files; the skill is instruction-only so nothing is written to disk and no external packages are pulled.
Credentials
The skill requests no environment variables, credentials, or config paths. There is no apparent need for secrets or external service access for its described functionality.
Persistence & Privilege
always is false and normal autonomous invocation is allowed (platform default). The skill does not request persistent presence, nor does it instruct modifying other skills or system settings.
Assessment
This skill is internally consistent and low-risk because it is text-only and requests no credentials or installs. Before installing, consider: (1) provenance — the publisher and homepage are unknown, so you should trust the agent environment and governance that will run the skill; (2) crisis handling — the SKILL.md defers to a 'safety-first' response for self-harm but does not specify actions, so ensure your agent has an established, tested safety/crisis workflow; (3) privacy — the skill will echo whatever users type into prompts (no exfiltration is indicated), so avoid entering sensitive personal data; and (4) expectations — this is explicitly non-clinical and reflective, not a substitute for professional mental health, legal, or financial advice.Like a lobster shell, security has layers — review code before you run it.
latestvk972mmtaq60pvs31kgksg4nvmn81kmbb
License
MIT-0
Free to use, modify, and redistribute. No attribution required.