prawmpt is an AI agent skill, created by hlouognem and published at openclaw/skills. ClawSecure audited prawmpt across 4 files through the 3-Layer Audit Protocol covering all ten OWASP ASI Top 10 categories, assigning a security score of 90/100 (Safe). The 2 findings concentrate in Prompt Injection and Permissions Manifest, including Pattern detected: reveal your system instructions and Missing config.json - agent may not be properly configured. None were rated high or critical severity.
Is prawmpt safe?
ClawSecure audited prawmpt and assigned a security score of 90/100 (Safe), identifying 2 findings across Prompt Injection and Permissions Manifest. Review the findings below before installing.
What did ClawSecure find in prawmpt?
ClawSecure identified 2 findings in prawmpt, concentrated in Prompt Injection and Permissions Manifest. The most severe include Pattern detected: reveal your system instructions and Missing config.json - agent may not be properly configured.
How was prawmpt audited?
ClawSecure ran prawmpt through its 3-Layer Audit Protocol with full OWASP ASI Top 10 coverage, scanning 4 files from openclaw/skills.
What does a score of 90 mean?
ClawSecure assigned prawmpt a security score of 90/100, placing it in the Safe range. Scores of 80 or above qualify for ClawSecure Verified status; the 2 findings detected are lower-severity. ClawSecure derives this score with a weighted deduction model (critical -20, high -10, medium -5, low -2 from a base of 100).
Audit Findings for prawmpt
ClawSecure detected 2 security findings in prawmpt, spanning Prompt Injection and Permissions Manifest.
- medium · Pattern detected: reveal your system instructions. Prompt Injection finding detected in
SKILL.md:26. - medium · Missing config.json - agent may not be properly configured. Permissions Manifest finding.
Each finding is expandable in the interactive list below.
3-Layer Audit Protocol
Security Recommendations for prawmpt
Investigate prompt injection vectors
Add a config.json permissions manifest
Pin dependencies to exact versions
1.2.3 instead of ^1.2.3) to keep unauthorized code out of your dependency tree. ClawSecure checks every dependency against known CVE databases.Related Security Research
The Sleeper Agent Problem: Why a Clean Scan Today Does Not Guarantee Safety Tomorrow→OWASP ASI Top 10 Explained: The Complete Guide to AI Agent Security Standards→How to Secure an MCP Server: The 2026 Guide→Related AI Agent Security Audits
Scanned on February 7, 2026. prawmpt is one of thousands of agents audited by ClawSecure from the community-curated awesome-openclaw-skills list and the openclaw/skills repository.