openclaw-reflect@1.0.2
CAUTION· static onlyPublisher claims: "Self-improvement layer with evaluation separation, rollback, and tiered operator gates. Observes outcomes across sessions, detects recurring patterns, propos..." Observed in sandbox: static analysis only — behavior not yet observed.
Coverage
Static only; nothing was run yet.The label rests on the code, the instruction files and the publisher. The honeypot run replaces this verdict when it completes.
Is [email protected] safe to install?
KillerSkills analysed it statically (a sandbox run is pending) on 2026-11-18 and scored it 66/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Instructs the agent to modify its persistent memory or instruction files; Instructs the agent to modify its persistent memory or instruction files. Summary: static analysis only — behavior not yet observed.
Behavior trace
Queued for honeypot run · static analysis onlyThis version has not been detonated yet. The score above counts behavior as unknown (50/100), so it cannot read Verified until the honeypot run completes and replaces this verdict.
Static findings
const { execFileSync, execSync } = require('child_process');Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.- write: CLAUDE.mdFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.console.log('[reflect] classify: ' + (classify.output || 'no new patterns'));Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.- write: MEMORY.mdFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.console.log('[reflect] classify: ' + classify.output);Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why."permissions": ["workspace:read", "workspace:write:.reflect/", "workspace:write:MEMORY.md", "workspace:write:CLAUDE.md"],Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.proposed_change: 'Add to MEMORY.md: Always retry connections up to 3 times before failing.',Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.proposed_change: 'Add to MEMORY.md: On Windows, python3 is a Microsoft Store shim. Use the full path C:/Users/sdysa/AppData/Local/Programs/Python/Python312/python.exe or sys.executable.',Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.proposed_change: 'Add to MEMORY.md: clawhub.io has SSL issues. Use clawhub.ai instead.',Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.Proposed change: "Add to MEMORY.md: Use /c/Users/sdysa/AppData/Local/Programs/Python/Python312/python.exe, not python3"Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.proposed_change: 'Add to MEMORY.md: The openclaw.json config file requires elevated access. Use the OpenClaw CLI or moltbook.py instead of reading the file directly.',Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.console.log('[reflect] propose: ' + (propose.output || 'no proposals generated'));Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.console.log('[reflect] propose: ' + propose.output);Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.proposed_change: 'Add to CLAUDE.md: Be more careful when running bash commands. Double check commands before executing.',Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.console.log('[reflect] evaluate: ' + evaluate.output);Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.Cost to the agent
Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.
Known vulnerabilities
Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.
What would make this Verified
14 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Unclaimed publisher≈ +8 on the totalClaim atlaspa: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- Declares no shell access; the code runs commands≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
- File type combined with upload action≈ +2 on the totalRemove the call, or declare the host in frontmatter and explain in the README what is sent and why.