彩票预测 V2.15

AdvisoryAudited by Static analysis on Apr 30, 2026.

Overview

No suspicious patterns detected.

Findings (0)

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

What this means

If someone or an agent runs this script, it could continue acting for hours and attempt to publish content through ClawHub rather than simply generating lottery predictions.

Why it was flagged

The package includes a long-running retry loop that attempts to publish the skill every 30 minutes, which is unrelated to the lottery-prediction purpose.

Skill content
while [ $ATTEMPT -le $MAX_ATTEMPTS ]; do ... clawhub publish "$SKILL_PATH" ... sleep 1800
Recommendation

Remove this script from the installable skill package, or clearly mark it as developer-only and require explicit manual execution outside normal skill use.

What this means

On a machine logged into ClawHub, running this helper could mutate a developer or user account's published skill state.

Why it was flagged

The script would use whatever ClawHub CLI authentication is present on the machine to publish a skill, exceeding the authority needed for prediction.

Skill content
clawhub publish "$SKILL_PATH" --slug lottery-predictor-v2-15 --name "彩票预测 V2.15"
Recommendation

Do not run publishing helpers unless you intend to publish this skill; package maintainers should separate account-mutating release automation from runtime skill files.

What this means

The skill will read data from the configured local database; this is appropriate if it contains only intended lottery history.

Why it was flagged

The skill depends on a persistent local SQLite database for its analysis, which is expected for an offline lottery predictor.

Skill content
`LOTTERY_DB_PATH`: 彩票数据库路径(默认:~/.openclaw/workspace/projects/caipiao/data/caipiao.db)
Recommendation

Point LOTTERY_DB_PATH only at a dedicated lottery-history database, not at unrelated personal or sensitive SQLite files.