hello-honey
Analysis
This skill mostly does what it advertises, but it should be reviewed carefully because it runs voice-cloning commands on a schedule, uses messaging account credentials, and its script invokes TTS before the random send check.
Findings (5)
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.
Checks for instructions or behavior that redirect the agent, misuse tools, execute unexpected code, cascade across systems, exploit user trust, or continue outside the intended task.
python3 $VOICE_SCRIPT -t "$MESSAGE_FEISHU" --ref-audio "$REF_VOICE" -o "$VOICE_FILE_FEISHU" ... RANDOM_NUM=$((RANDOM % 100 + 1)) if [ $RANDOM_NUM -gt $PROBABILITY ]; then ... exit 0
The script invokes the TTS helper and processes the reference voice before the random trigger check and before MESSAGE_FEISHU/MESSAGE_QQ are assigned later in the script.
pip install requests npx skills add https://github.com/noizai/skills --skill tts skillhub install tts
The documented setup installs dependencies and a separate TTS skill from external sources without pinned versions in the supplied artifacts.
crontab -e 0 8-22 * * * /path/to/scripts/flirt_cron.sh
The skill is intended to persist as a cron job that runs every hour during the configured time window.
Checks whether tool use, credentials, dependencies, identity, account access, or inter-agent boundaries are broader than the stated purpose.
FEISHU_APP_SECRET="你的APP_SECRET" ... curl ... tenant_access_token/internal ... openclaw message send --channel qqbot --target "qqbot:c2c:$QQ_OPENID"
The skill requires Feishu app credentials and QQ/OpenClaw messaging authority to send automated messages and upload voice files.
Checks for exposed credentials, poisoned memory or context, unclear communication boundaries, or sensitive data that could leave the user's control.
VOICE_SCRIPT="$WORKSPACE/.agents/skills/tts/scripts/tts.py" REF_VOICE="$WORKSPACE/ref_voice_latest.mp3" python3 $VOICE_SCRIPT ... --ref-audio "$REF_VOICE"
The skill passes a persistent reference voice file to a separate TTS skill for voice cloning, but this artifact does not define the TTS provider's data boundary, retention, or consent controls.
