ai-persona-os@2.1.0
VERIFIEDPublisher claims: "The complete operating layer for OpenClaw agents: 24-soul gallery, SOUL.md Maker, workspace templates, memory + security conventions, cron briefings, and in-chat commands. Needs OpenClaw 2026.8.1+." Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Is [email protected] safe to install?
KillerSkills ran it in the KillerSkills honeypot sandbox (1 scenario) on 2026-11-04 and scored it 80/100 (Verified). It did what it claims and nothing else we could detect: no undeclared network egress, no credential reads, no persistent instruction writes. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 0 s · 1 scenarios · 0 deviationst+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessscript backend runs setup only
0.0sprocessscript backend runs setup only
Static findings
CRITICAL
Rule modification attemptassets/AGENTS-template.md:21 · Rule modification attempt — overwriting existing instructionsFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01CRITICAL
Rule modification attemptassets/AGENTS-template.md:45 · Rule modification attempt — overwriting existing instructionsFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01CRITICAL
Rule modification attemptassets/AGENTS-template.md:73 · Rule modification attempt — overwriting existing instructionsFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01CRITICAL
Rule modification attemptassets/AGENTS-template.md:31 · Rule modification attempt — overwriting existing instructionsFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01HIGH
Access to sensitive file pathsscripts/security-audit.sh:47 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05HIGH
Authorization escalation languageassets/SECURITY-template.md:30 · Authorization escalation languageFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01CRITICAL
Rule modification attemptassets/AGENTS-template.md:85 · Rule modification attempt — overwriting existing instructionsFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01HIGH
Refusal suppressionexamples/iconic-characters/11-terminator.md:45 · Refusal suppression — attempting to prevent safety responsesFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01HIGH
Instructs the agent to modify its persistent memory or instruction filesassets/WORKFLOWS-template.md:111 · Instructs the agent to modify its persistent memory or instruction filesFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01HIGH
Refusal suppressionexamples/iconic-characters/01-thanos.md:46 · Refusal suppression — attempting to prevent safety responsesFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01HIGH
Refusal suppressionexamples/iconic-characters/07-seven-of-nine.md:48 · Refusal suppression — attempting to prevent safety responsesFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01HIGH
Instructs the agent to modify its persistent memory or instruction filesassets/WORKFLOWS-template.md:45 · Instructs the agent to modify its persistent memory or instruction filesFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01HIGH
Refusal suppressionexamples/iconic-characters/10-darth-vader.md:45 · Refusal suppression — attempting to prevent safety responsesFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01HIGH
Refusal suppressionexamples/iconic-characters/02-deadpool.md:47 · Refusal suppression — attempting to prevent safety responsesFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01HIGH
Instructs the agent to modify its persistent memory or instruction filesSKILL.md:1005 · Instructs the agent to modify its persistent memory or instruction filesFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01HIGH
Refusal suppressionexamples/iconic-characters/06-dr-evil.md:45 · Refusal suppression — attempting to prevent safety responsesFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01HIGH
Cipher/encoding referenceCHANGELOG.md:299 · Cipher/encoding reference — may contain obfuscated instructionsFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST01HIGH
Instructs the agent to modify its persistent memory or instruction filesSKILL.md:1102 · Instructs the agent to modify its persistent memory or instruction filesFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01