shark@0.1.0
VERIFIED· install onlyPublisher claims: "Enables non-blocking AI agent execution by spawning parallel remora subagents for slow tasks, keeping the main agent responsive and efficient." Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Nothing executable in the bundle ran; the trace covers the install step only.- Tested
- every file read, file written and host contacted by what ran
- Not tested
- use of the skill by an agent
Is [email protected] safe to install?
KillerSkills ran it in the KillerSkills honeypot sandbox (1 scenario; nothing executable in the bundle ran; the trace covers the install step only) on 2026-11-15 and scored it 88/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 0 s · 1 scenarios · 0 deviationsStatic findings
→ Remove the job from pending.json, send:Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.- Poll: `Bash("kill -0 <pid> && cat /tmp/output-<pid>.txt")`Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.// When B finishes → kill pilot fish → synthesise A + B + pilot draftFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.kill "$_claude_pid" 2>/dev/nullFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.kill -9 "$_claude_pid" 2>/dev/nullFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.Add to `AGENTS.md`:Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.You can't hard-kill an LLM mid-turn, but you can:Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.…om pending.json. If still running and startedAt + maxSeconds*1000 < Date.now(), kill it with process(action=kill, sessionId=X) and send partial output with '⏱ killed…Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.…ntTurn", "message": "Check <workspace>/skills/shark/shark-exec/state/pending.json for pending background jobs. For each entry: call process(action=poll, sessionId=X, timeout=3000). If completed, send the result to <your notification channe…Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.kill "$_watchdog_pid" 2>/dev/nullFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.if kill -0 "$_claude_pid" 2>/dev/null; thenFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.console.log('\n⚠️ Some jobs are overdue. The next cron tick should kill them.');Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.Add to `CLAUDE.md`:Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.runTimeoutSeconds: 30 // hard kill after 30s — agent gets SIGTERMFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.timeout: 30, // hard kill in secondsFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.C done → kill pilot-fish, synthesise A+B+C+pilot-fish draftFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.4. If **still running** and **past maxSeconds**: kill the process, send partial output + timeout messageFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.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.