adam-framework@1.0.1
CAUTION· static onlyPublisher claims: "5-layer persistent memory and coherence architecture for OpenClaw agents. Solves AI amnesia and within-session drift. Built and validated over 353 sessions o..." 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 2026-11-20 and scored it 53/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Access to sensitive file paths; Privileged sudo command; Hidden zero-width characters detected. 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
GEMINI_KEY=$(jq -r '.env.GEMINI_API_KEY // empty' "$OPENCLAW_DIR/openclaw.json" 2>/dev/null)Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.# - jq (brew install jq / sudo apt install jq)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.#!/usr/bin/env python3Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.# - jq installed (brew install jq / sudo apt install jq)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.**Update CORE_MEMORY.md when:**Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.rlog(f"Failed to write CORE_MEMORY.md: {e}", "ERROR")Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.Write-Host "CORE_MEMORY.md:" (Test-Path "$v\CORE_MEMORY.md")Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.if ! kill -0 "$GATEWAY_PID" 2>/dev/null; thenFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.Read `vault-templates/CORE_MEMORY.template.md`. Apply the same substitutions as 1.2 plus any additional project/context detail the user provided. Write to `$VAULT\CORE_MEMORY.md`.Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.cecho "$YELLOW" " Linux: sudo apt install jq"Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.…es to C:\\YOUR_VAULT_PATH\\workspace\\memory\\YYYY-MM-DD.md in Markdown format. Update C:\\YOUR_VAULT_PATH\\CORE_MEMORY.md if project state has changed. Reply with NO_REPLY if nothing to store.", …Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct."Write any lasting notes to your Vault memory file. Update CORE_MEMORY.md ifFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.# 2. chmod +x SENTINEL.sh && run once manually to verifyFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.…and: desktop-commander, args: [serve]' — that package name does not resolve via npx and causes all desktop-commander tool calls to fail with 'Tool not found'. The corr…Fix: Pin versions and sources; vendor anything fetched at install time."prompt": "Write any lasting notes to YOUR_VAULT/memory/YYYY-MM-DD.md. Update CORE_MEMORY.md if project state has changed. Reply with NO_REPLY if nothing to store.",Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.result = subprocess.run(["git"] + args, cwd=cwd, capture_output=True, text=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.**5. Tell Adam about it** — update `CORE_MEMORY.md` with the new agent's capabilitiesFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.…div><div class="timeline-event">Layer 1 emerges</div><div class="timeline-desc">Write everything down in files, make the AI read them. SOUL.md and CORE_MEMORY.md created. Session coherence improved immediately.</div></div> <div class="…Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.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
27 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Unclaimed publisher≈ +8 on the totalClaim strangeadvancedmarketing: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- Access to sensitive file paths≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
- Privileged sudo command≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
- Hidden zero-width characters detected≈ +4 on the totalKeep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
- Process kill command≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
- File permission modification command≈ +2 on the totalRequest the narrowest permission that works; replace wildcards with the exact paths or hosts.