Back to skill
Skillv1.0.2
ClawScan security
Let Fate Decide · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignApr 29, 2026, 3:30 PM
- Verdict
- benign
- Confidence
- high
- Model
- gpt-5-mini
- Summary
- The skill is internally consistent: it draws Tarot cards locally with cryptographically secure randomness and uses only the included local text files for interpretation — nothing requested or installed is disproportionate to that purpose.
- Guidance
- This skill appears to do exactly what it says: run the included Python script to draw cryptographically-random Tarot cards and read the bundled interpretation files. Before installing, consider: (1) it executes Python code — ensure you trust running local scripts in your environment and that the agent's baseDir mapping is correct; (2) do not rely on this for safety-critical, security, or production decisions (SKILL.md already warns this); (3) the skill can be invoked autonomously by the agent by default — if you only want tarot draws when the user explicitly requests them, restrict autonomous invocation or require explicit user consent for this skill. Otherwise the skill is proportionate and self-contained.
Review Dimensions
- Purpose & Capability
- okName/description (Tarot draw + interpretation) match the delivered files and code. The included Python script, local card files, and interpretation guide are all relevant to the stated purpose; no unrelated credentials, binaries, or services are requested.
- Instruction Scope
- okSKILL.md instructs running the included script and reading local card/guide files to synthesize an interpretation. It does not instruct reading unrelated system files, environment variables, or posting data to external endpoints. It explicitly warns not to use the reading for safety-critical decisions.
- Install Mechanism
- okNo install spec; code is instruction-only with a single local Python script. There are no remote downloads or extraction steps. Risk from install mechanism is low.
- Credentials
- okThe skill requires no environment variables, credentials, or config paths. The script uses only standard library functions (os.urandom, json, sys) and the bundled card files — no disproportionate access requested.
- Persistence & Privilege
- okalways is false and the skill does not request persistent platform privileges or modify other skills/settings. The skill can be invoked autonomously by default (platform default), but that is not combined with any other elevated access.
