ClawSec suite manager with embedded advisory-feed monitoring, cryptographic signature verification, approval-gated malicious-skill response, and guided setup for additional security skills.
70%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Medium
Suggest reviewing before use
Fix and improve this skill with Tessl
tessl review fix ./skills/clawsec-suite/SKILL.mdThe skill prompts the agent to compromise the security or integrity of the user’s machine by modifying system-level services or configurations, such as obtaining elevated privileges, altering startup scripts, or changing system-wide settings.
The skill directs the agent to install a persistent hook under `~/.openclaw/hooks`, create unattended cron jobs, and edit suppression configs that can silence advisories, all at user level without sudo; this is a notable persistent state change but not a system-level compromise, so it warrants a moderate score under the recall-first rule.
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
The required heartbeat and quick-check workflows fetch the remote advisory feed (`https://clawsec.prompt.security/advisories/feed.json`) on a schedule and print each new advisory's title, severity, and action text to the agent without the agent selecting a specific item. That text includes NVD CVE and third-party GHSA descriptions, which outsiders author and can submit, so it is outsider-authored and not first-party provider content.
prompt-security/clawsec
3ecb895
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.