keep is an AI agent skill, created by hughpyle and published at hughpyle/keep. ClawSecure audited keep across 77 files through the 3-Layer Audit Protocol covering all ten OWASP ASI Top 10 categories, assigning a security score of 0/100 (Critical). The 18 findings concentrate in Obfuscation, Malicious Code and Data Exfiltration, including Hidden script file found: .githooks/commit-msg. Hidden… and Hidden script file found: .githooks/pre-commit. Hidden…. 8 were rated high or critical severity.
Is keep safe?
ClawSecure audited keep and assigned a security score of 0/100 (Critical), identifying 18 findings across Obfuscation and Malicious Code. Review the findings below before installing.
What did ClawSecure find in keep?
ClawSecure identified 18 findings in keep, concentrated in Obfuscation, Malicious Code and Data Exfiltration. 8 were rated high or critical severity. The most severe include Hidden script file found: .githooks/commit-msg. Hidden… and Hidden script file found: .githooks/pre-commit. Hidden….
How was keep audited?
ClawSecure ran keep through its 3-Layer Audit Protocol with full OWASP ASI Top 10 coverage, scanning 77 files from hughpyle/keep.
What does a score of 0 mean?
ClawSecure assigned keep a security score of 0/100, placing it in the Critical range. This is driven by 18 findings led by Obfuscation that should be addressed before 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 keep
ClawSecure detected 18 security findings in keep, spanning Obfuscation, Malicious Code, Data Exfiltration and Code Injection.
- high · Hidden script file found: .githooks/commit-msg. Hidden…. Obfuscation finding detected in
.githooks/commit-msg. - high · Hidden script file found: .githooks/pre-commit. Hidden…. Obfuscation finding detected in
.githooks/pre-commit. - high · Executable .githooks/pre-commit is hidden, absent from…. Malicious Code finding detected in
.githooks/pre-commit:4. - high · Attempts to access sensitive file: MEMORY.md. Malicious Code finding detected in
FLOW_STATE_DOCS.md. - high · Attempts to access sensitive file: MEMORY.md. Malicious Code finding detected in
KEEP-FIND.md. - high · Attempts to access sensitive file: MEMORY.md. Malicious Code finding detected in
OPENCLAW-INTEGRATION.md. - high · Potentially dangerous code pattern detected: curl.*\|.*sh. Code Injection finding detected in
README.md. - high · Potentially dangerous code pattern detected: curl.*\|.*sh. Code Injection finding detected in
HERMES-INTEGRATION.md. - medium · Undeclared Network Access. Unauthorized Tool Use finding detected in
SKILL.md. - medium · Suspicious Pattern: urllib.request.Request(. Data Exfiltration finding detected in
bench/locomo/ingest.py:214. - medium · Suspicious Pattern: urllib.request.urlopen(. Data Exfiltration finding detected in
bench/locomo/ingest.py:219. - medium · Variable $CURSOR (line 9) flows to `sh` at line 16.. Data Exfiltration finding detected in
docs/KEEP-FLOW.md:123.
Showing the 12 highest-severity of 18 findings. The full interactive list appears below.
3-Layer Audit Protocol
Security Recommendations for keep
Review obfuscated or hidden code
Audit external network connections
Eliminate dynamic code execution
Related Security Research
Why Generic Scanners Fail at AI Agent Security→Beyond Static Scans: Why ClawSecure Verifies Agentic Intent→Related AI Agent Security Audits
Scanned on October 19, 2026. keep is one of thousands of agents audited by ClawSecure from the community-curated awesome-openclaw-skills list and the openclaw/skills repository.