engram is an AI agent skill, created by anwitch and published at anwitch/engram. ClawSecure audited engram across 13 files through the 3-Layer Audit Protocol covering all ten OWASP ASI Top 10 categories, assigning a security score of 50/100 (Medium Risk). The 11 findings concentrate in Unauthorized Tool Use, Data Exfiltration and Policy Violation, including Pattern detected: sudo apt-get install and Pattern detected: sudo apt-get install. None were rated high or critical severity.
Is engram safe?
ClawSecure audited engram and assigned a security score of 50/100 (Medium Risk), identifying 11 findings across Unauthorized Tool Use and Data Exfiltration. Review the findings below before installing.
What did ClawSecure find in engram?
ClawSecure identified 11 findings in engram, concentrated in Unauthorized Tool Use, Data Exfiltration and Policy Violation. The most severe include Pattern detected: sudo apt-get install and Pattern detected: sudo apt-get install.
How was engram audited?
ClawSecure ran engram through its 3-Layer Audit Protocol with full OWASP ASI Top 10 coverage, scanning 13 files from anwitch/engram.
What does a score of 50 mean?
ClawSecure assigned engram a security score of 50/100, placing it in the Medium Risk range. This reflects 11 findings led by Unauthorized Tool Use that warrant review before production use. 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 engram
ClawSecure detected 11 security findings in engram, spanning Unauthorized Tool Use, Data Exfiltration, Policy Violation and Permissions Manifest.
- medium · Pattern detected: sudo apt-get install. Unauthorized Tool Use finding detected in
install.sh:48. - medium · Pattern detected: sudo apt-get install. Unauthorized Tool Use finding detected in
install.sh:49. - medium · Pattern detected: sudo yum install. Unauthorized Tool Use finding detected in
install.sh:52. - medium · Pattern detected: sudo yum install. Unauthorized Tool Use finding detected in
install.sh:53. - medium · Pattern detected: sudo dnf install. Unauthorized Tool Use finding detected in
install.sh:56. - medium · Pattern detected: sudo dnf install. Unauthorized Tool Use finding detected in
install.sh:57. - medium · Script iterates through environment variables in.... Data Exfiltration finding detected in
/tmp/url-scans/16378985215f088e/tool_engram_search.py. - medium · Script iterates through environment variables in.... Data Exfiltration finding detected in
/tmp/url-scans/16378985215f088e/test_connection.py. - medium · Script iterates through environment variables in.... Data Exfiltration finding detected in
/tmp/url-scans/16378985215f088e/tool_engram_index.py. - medium · Missing config.json - agent may not be properly configured. Permissions Manifest finding.
- info · Skill manifest does not include a 'license' field. Specifying a license.... Policy Violation finding detected in
SKILL.md.
Each finding is expandable in the interactive list below.
3-Layer Audit Protocol
Security Recommendations for engram
Audit external network connections
Resolve policy violations
Add a config.json permissions manifest
Related Security Research
ClawHavoc Explained: The Malware Family Targeting AI Agents→Beyond Static Scans: Why ClawSecure Verifies Agentic Intent→Related AI Agent Security Audits
Scanned on February 18, 2026. engram is one of thousands of agents audited by ClawSecure from the community-curated awesome-openclaw-skills list and the openclaw/skills repository.