AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified Apache-2.0 Self-run

Exec Observe

skill-batteryshark-rekit-exec-observe · by batteryshark

DYNAMIC: run a target in a fresh working directory with a timeout and capture its behavior — exit code, stdout/stderr, wall-clock time, and files it creates. EXECUTES the target; use the tracer skills for syscall, API, or network visibility. Run only where you accept the target's risk.

No reviews yet
0 installs
7 views
0.0% view→install

Install

$ agentstack add skill-batteryshark-rekit-exec-observe

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-batteryshark-rekit-exec-observe)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
1mo ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Exec Observe? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Execute & Observe (dynamic)

⚡ Dynamic tier — this RUNS the target. Run it only where you don't mind the risk: a disposable VM or a dedicated analysis box, or behind an isolation provider.

When to use

Use this when you need the target's exit status, output, file effects, and timing. For deeper visibility, use syscall-trace, net-capture, or frida-trace.

What it does

Runs the target in a fresh temp working directory with a timeout, and captures:

  • exit code (and whether it timed out),
  • stdout / stderr (head),
  • wall-clock duration,
  • files created in the working dir.

It bounds the run (working dir + timeout) but does not sandbox the target — the target can do anything the host allows.

Consent

Because it executes untrusted code, it's gated:

  • via rekit: rekit run --allow-dynamic exec-observe (the dispatcher sets the

consent env for the runner);

  • direct call: pass --yes-i-consent or set REKIT_ALLOW_DYNAMIC=1.

Without consent it refuses with exit 4.

Usage

rekit run --allow-dynamic exec-observe ./sample --timeout 15
rekit run --allow-dynamic exec-observe ./sample --format json

Prerequisites

  • python3 ≥ 3.8 — pure stdlib. (Whatever the target needs to run is on you.)

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.