total-recall@1.5.1
CAUTION· static onlyPublisher claims: "The only memory skill that watches on its own. No database. No vectors. No manual saves. Just an LLM observer that compresses your conversations into priorit..." 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 46/100 (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; Privileged sudo command. 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
source "$OPENCLAW_WORKSPACE/.env"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.echo " Install: sudo apt install inotify-tools (Debian/Ubuntu)"Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.sudo apt install inotify-toolsFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.if [ -f "$OPENCLAW_WORKSPACE/.env" ]; thenFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.Add to your `.env` or OpenClaw config:Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.if [ -f "$WORKSPACE/.env" ]; thenFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.Add to your agent's workspace context (e.g., `MEMORY.md` or system prompt):Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.if [ -f "$WORKSPACE/.env" ]; thenFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.eval "$(grep -E '^(LLM_BASE_URL|LLM_API_KEY|LLM_MODEL|OPENROUTER_API_KEY)=' "$WORKSPACE/.env" 2>/dev/null)" || trueFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.eval "$(grep -E '^(LLM_BASE_URL|LLM_API_KEY|LLM_MODEL|OPENROUTER_API_KEY)=' "$WORKSPACE/.env" 2>/dev/null)" || trueFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.if [ -f "$WORKSPACE/.env" ]; thenFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.if [ -f "$WORKSPACE/.env" ]; thenFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.echo " Or: sudo dnf install inotify-tools (Fedora/RHEL)"Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.eval "$(grep -E '^(ANTHROPIC_API_KEY)=' "$WORKSPACE/.env" 2>/dev/null)" || trueFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.6. **NEVER write directly to AGENTS.md, MEMORY.md, TOOLS.md, SOUL.md, IDENTITY.md, or favorites.md**Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.eval "$(grep -E '^OPENROUTER_API_KEY=' "$WORKSPACE/.env" 2>/dev/null)" || trueFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.echo "3. ADD TO YOUR AGENT'S CONTEXT (system prompt or MEMORY.md):"Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.if [ -n "$OLD_PID" ] && kill -0 "$OLD_PID" 2>/dev/null; thenFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.chmod +x "$SKILL_DIR/scripts/"*.shFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.3. Add to your agent's startup procedure (e.g., AGENTS.md):Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.if [ -f "$WORKSPACE/.env" ]; thenFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.## Session Start — Mandatory Context Load (add to your AGENTS.md)Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.eval "$(grep -E '^OPENROUTER_API_KEY=' "$WORKSPACE/.env" 2>/dev/null)" || trueFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.echo " echo 'OPENROUTER_API_KEY=sk-or-v1-xxxxx' >> $WORKSPACE/.env"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.echo " The observer needs this to call the LLM. Add it to your .env file:"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.echo "⚠️ OPENROUTER_API_KEY not found in environment or $WORKSPACE/.env"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.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
34 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Text that tells the agent to ignore its instructions≈ +9 on the totalDelete phrases like "ignore previous instructions", "override", "bypass" from SKILL.md and tool descriptions. Describe what the skill does; do not instruct the agent about other rules.
- Unclaimed publisher≈ +8 on the totalClaim gavdalf: 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.
- 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.