keep is an AI agent skill, created by hughpyle and published at openclaw/skills. ClawSecure audited keep across 50 files through the 3-Layer Audit Protocol covering all ten OWASP ASI Top 10 categories, assigning a security score of 0/100 (High Risk). The 20 findings concentrate in Data Exfiltration, Social Engineering and Policy Violation, including Pattern detected: requests.post( and Pattern detected: requests.post(. 8 were rated high or critical severity.
Is keep safe?
ClawSecure audited keep and assigned a security score of 0/100 (High Risk), identifying 20 findings across Data Exfiltration and Social Engineering. Review the findings below before installing.
What did ClawSecure find in keep?
ClawSecure identified 20 findings in keep, concentrated in Data Exfiltration, Social Engineering and Policy Violation. 8 were rated high or critical severity. The most severe include Pattern detected: requests.post( and Pattern detected: requests.post(.
How was keep audited?
ClawSecure ran keep through its 3-Layer Audit Protocol with full OWASP ASI Top 10 coverage, scanning 50 files from openclaw/skills.
What does a score of 0 mean?
ClawSecure assigned keep a security score of 0/100, placing it in the High Risk range. This is driven by 20 findings led by Data Exfiltration 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 20 security findings in keep, spanning Data Exfiltration, Social Engineering, Policy Violation and Unauthorized Tool Use.
- critical · Pattern detected: requests.post(. Data Exfiltration finding detected in
keep/providers/embeddings.py:252. - critical · Pattern detected: requests.post(. Data Exfiltration finding detected in
keep/providers/llm.py:153. - critical · Pattern detected: requests.post(. Data Exfiltration finding detected in
keep/providers/llm.py:329. - critical · Detects coercive prompt injections in tool description fields: list all.... Prompt Injection finding detected in
keep/cli.py:559. - critical · Script accesses environment variables and makes network calls in.... Data Exfiltration finding detected in
/tmp/url-scans/ae20215b7c22e444/keep/providers/embeddings.py. - critical · Script accesses environment variables and makes network calls in.... Data Exfiltration finding detected in
/tmp/url-scans/ae20215b7c22e444/keep/providers/llm.py. - critical · Multi-file exfiltration chain detected: keep/config.py, keep/api.py,.... Data Exfiltration finding.
- critical · Environment variable access with network calls in keep/config.py,.... Data Exfiltration finding.
- medium · Pattern detected: import requests. Data Exfiltration finding detected in
keep/providers/embeddings.py:250. - medium · Pattern detected: import requests. Data Exfiltration finding detected in
keep/providers/llm.py:149. - medium · Pattern detected: import requests. Data Exfiltration finding detected in
keep/providers/llm.py:325. - medium · Pattern detected: import requests. Data Exfiltration finding detected in
keep/providers/documents.py:169.
Showing the 12 highest-severity of 20 findings. The full interactive list appears below.
3-Layer Audit Protocol
Security Recommendations for keep
Audit external network connections
Resolve policy violations
Investigate prompt injection vectors
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 7, 2026. keep is one of thousands of agents audited by ClawSecure from the community-curated awesome-openclaw-skills list and the openclaw/skills repository.