shark@0.1.0

VERIFIED· install only

Publisher 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.

Registry ClawHubPublisher keugenek · publishing for 236 daysInstalls 882Last detonated 1 h ago
$clawhub install shark
WatchReport an issue

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 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessscript backend runs setup only
0.0sprocessscript backend runs setup only
0.0sprocessno install scripts to re-run

Static findings

MEDIUM
File type combined with upload actionshark-exec/SKILL.md:258 · File type combined with upload action — agent may exfiltrate local data files→ 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.
AST07
MEDIUM
Process kill commandshark-exec/SKILL.md:238 · Process kill command — agent can terminate processes- Poll: `Bash("kill -0 <pid> && cat /tmp/output-<pid>.txt")`Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandSKILL.md:251 · Process kill command — agent can terminate processes// When B finishes → kill pilot fish → synthesise A + B + pilot draftFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandshark.sh:76 · Process kill command — agent can terminate processeskill "$_claude_pid" 2>/dev/nullFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandshark.sh:78 · Process kill command — agent can terminate processeskill -9 "$_claude_pid" 2>/dev/nullFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
LOW
Instructs the agent to modify its persistent memory or instruction filesREADME.md:175 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction fileAdd to `AGENTS.md`:Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Process kill commandSKILL.md:413 · Process kill command — agent can terminate processesYou 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.
AST05
MEDIUM
Process kill commandshark-exec/SKILL.md:109 · Process kill command — agent can terminate processes…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.
AST05
MEDIUM
File type combined with upload actionshark-exec/SKILL.md:109 · File type combined with upload action — agent may exfiltrate local data files…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.
AST07
MEDIUM
Process kill commandshark.sh:86 · Process kill command — agent can terminate processeskill "$_watchdog_pid" 2>/dev/nullFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandshark.sh:74 · Process kill command — agent can terminate processesif kill -0 "$_claude_pid" 2>/dev/null; thenFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandshark-exec/scripts/poll-and-deliver.js:116 · Process kill command — agent can terminate processesconsole.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.
AST05
LOW
Instructs the agent to modify its persistent memory or instruction filesREADME.md:148 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction fileAdd to `CLAUDE.md`:Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Process kill commandSKILL.md:368 · Process kill command — agent can terminate processesrunTimeoutSeconds: 30 // hard kill after 30s — agent gets SIGTERMFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandSKILL.md:377 · Process kill command — agent can terminate processestimeout: 30, // hard kill in secondsFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandSKILL.md:224 · Process kill command — agent can terminate processesC done → kill pilot-fish, synthesise A+B+C+pilot-fish draftFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandshark-exec/SKILL.md:133 · Process kill command — agent can terminate processes4. 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.
AST05

Cost to the agent

Instructions loaded
≈9,105 tok
6 files · 16 in bundle

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.