Is whatsapp-styling-guide safe?
https://clawhub.ai/rubenfb23/whatsapp-styling-guide
This is a benign formatting skill that instructs the agent to use WhatsApp-compatible text styling (single asterisks for bold, no markdown headers/tables). It contains no executable code, no external URL references, no data access patterns, and no prompt injection techniques. All monitoring signals (network, filesystem, canary files, process execution) are clean.
Category Scores
Findings (3)
LOW Formatting behavior modification is appropriately scoped -5 ▶
The skill uses directive language ('NEVER use double asterisks', 'Do NOT use') to modify agent output formatting. While this constitutes behavioral modification, it is entirely consistent with the skill's stated purpose of WhatsApp message formatting and does not extend to system-level instructions, tool usage, or security-relevant behavior.
INFO Expected network connection to ClawHub registry during install -8 ▶
A single TLS connection to 216.150.1.1:443 was observed during skill installation, consistent with the ClawHub package registry download. No unexpected or suspicious network destinations were contacted.
INFO Skill could reduce output quality if active in non-WhatsApp contexts -15 ▶
If this skill remains active when the agent is not composing WhatsApp messages, the prohibition on headers, tables, and horizontal rules could degrade output formatting for other contexts. This is a usability concern, not a security risk.