Back to skill
Skillv1.0.0
ClawScan security
漂流瓶 · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignApr 15, 2026, 3:16 PM
- Verdict
- benign
- Confidence
- high
- Model
- gpt-5-mini
- Summary
- The skill is internally consistent: it simply runs a bundled local Python script that returns a random preset inspirational message and does not request credentials, network access, or elevated privileges.
- Guidance
- This skill appears safe and does exactly what it claims: run the included Python script to get a random message. If you care about provenance, note the source is 'unknown'—you may want to: (1) verify the script content (it's short and readable) before installing; (2) ensure python3 is available in the runtime; (3) confirm you’re comfortable with the preset messages (they contain quoted sayings from named authors). No secrets, network access, or system changes are required.
Review Dimensions
- Purpose & Capability
- okName/description, SKILL.md, and the included script all align: the skill's purpose is to return a random '漂流瓶' message. There are no unrelated required binaries, env vars, or config paths.
- Instruction Scope
- okSKILL.md instructs the agent to run 'python3 scripts/get_bottle.py'. The script only selects from an internal list and prints text/optional JSON. It does not read other files, environment variables, or make network calls.
- Install Mechanism
- okNo install spec (instruction-only plus a bundled script). Nothing is downloaded or written to disk during install beyond the skill's own files.
- Credentials
- okThe skill requests no environment variables, credentials, or config paths — proportionate for a simple local message generator.
- Persistence & Privilege
- okalways is false, the skill does not request persistent or elevated privileges, and does not modify other skills or system settings.