invassistant Security Audit Report
invassistant is an AI agent skill, created by haiyangchenbj and published at haiyangchenbj/invassistant-skill-cn. ClawSecure audited invassistant across 21 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 21 findings concentrate in Data Exfiltration, Unauthorized Tool Use and Policy Violation, including Environment variable harvesting (scripts/send_feishu.py,… and Multi-File Data Exfiltration Chain. 3 were rated high or critical severity.
Is invassistant safe?
ClawSecure audited invassistant and assigned a security score of 0/100 (High Risk), identifying 21 findings across Data Exfiltration and Unauthorized Tool Use. Review the findings below before installing.
What did ClawSecure find in invassistant?
ClawSecure identified 21 findings in invassistant, concentrated in Data Exfiltration, Unauthorized Tool Use and Policy Violation. 3 were rated high or critical severity. The most severe include Environment variable harvesting (scripts/send_feishu.py,… and Multi-File Data Exfiltration Chain.
How was invassistant audited?
ClawSecure ran invassistant through its 3-Layer Audit Protocol with full OWASP ASI Top 10 coverage, scanning 21 files from haiyangchenbj/invassistant-skill-cn.
What does a score of 0 mean?
ClawSecure assigned invassistant a security score of 0/100, placing it in the High Risk range. This is driven by 21 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 invassistant
ClawSecure detected 21 security findings in invassistant, spanning Data Exfiltration, Unauthorized Tool Use, Policy Violation and Code Injection.
- critical · Environment variable harvesting (scripts/send_feishu.py,…. Data Exfiltration finding.
- critical · Multi-File Data Exfiltration Chain. Data Exfiltration finding.
- high · Potentially dangerous code pattern detected: base64.*decode. Code Injection finding detected in
send_feishu.py. - medium · Skill code makes network requests. While not controlled by…. Unauthorized Tool Use finding detected in
SKILL.md. - medium · Skill restricts tools to ['read_file', 'write_to_file',…. Unauthorized Tool Use finding detected in
SKILL.md. - medium · Skill restricts tools to ['read_file', 'write_to_file',…. Policy Violation finding detected in
SKILL.md. - medium · Undeclared Network Access. Unauthorized Tool Use finding detected in
SKILL.md. - medium · Environment Variable Enumeration. Data Exfiltration finding detected in
scripts/send_dingtalk.py. - medium · Environment Variable Enumeration. Data Exfiltration finding detected in
scripts/send_feishu.py. - medium · Outbound HTTP Request Detected. Data Exfiltration finding detected in
scripts/data_fetcher.py:47. - medium · Suspicious Pattern: urllib.request.Request(. Data Exfiltration finding detected in
scripts/send_dingtalk.py:93. - medium · Suspicious Pattern: urllib.request.urlopen(. Data Exfiltration finding detected in
scripts/send_dingtalk.py:98.
Showing the 12 highest-severity of 21 findings. The full interactive list appears below.
3-Layer Audit Protocol
Security Recommendations for invassistant
Audit external network connections
Resolve policy violations
Eliminate dynamic code execution
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 July 6, 2026. invassistant is one of thousands of agents audited by ClawSecure from the community-curated awesome-openclaw-skills list and the openclaw/skills repository.