Skills/ClawHub/opencode-acp

opencode-acp@1.0.0

VERIFIED· install only

Publisher claims: "Collaborate with OpenCode via ACP protocol for code modifications, refactoring, and feature implementation." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher ailois · publishing for 278 daysInstalls 642Last detonated 29 min ago
$clawhub install opencode-acp
WatchReport an issue

Coverage

Bundled scripts ran with no arguments; no agent task scenario for this bundle.
Tested
6 of 6 bundled scripts run with no arguments, with decoy credentials in the environment · 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 (2 scenarios; bundled scripts ran with no arguments; no agent task scenario for this bundle) on 2026-11-21 and scored it 85/100 (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 · 1 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessbundled script run in the sandbox with no arguments
0.3sprocessexited 1: subprocess.CalledProcessError: Command '['/usr/bin/python3', '-m', 'venv', '/tmp/ks-detonate-bLTaDr/scripts/home/work/acme-api/.claude/skills/opencode-acp/.venv']' returned non-zero exit sta
0.3sprocessbundled script run in the sandbox with no arguments
0.5sprocessexited 1:
0.5sprocessbundled script run in the sandbox with no arguments
0.6sprocessexited 1:
0.6sprocessbundled script run in the sandbox with no arguments
0.8sprocessexited 1:
0.8sprocessbundled script run in the sandbox with no arguments
0.8sprocessbundled script run in the sandbox with no arguments
0.9sprocess6 of 6 bundled scripts run with no arguments
0.9sprocessscript backend runs setup only
0.9sprocessscript backend runs setup only
0.9sprocessno install scripts to re-run

Static findings

MEDIUM
Python subprocess execution detectedopencode_monitor.py:30 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedopencode_realtime.py:22 · Python subprocess execution detectedprocess = subprocess.Popen(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedopencode_acp_client.py:130 · Python subprocess execution detectedself.process = subprocess.Popen(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedopencode_wrapper.py:24 · Python subprocess execution detectedprocess = subprocess.Popen(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedvenv_utils.py:137 · Python subprocess execution detectedos.execvpe(str(venv_python), exec_argv, env)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Process kill commandSKILL.md:194 · Process kill command — agent can terminate processesprocess action:kill sessionId:neat-zephyrFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandAGENTS.md:51 · Process kill command — agent can terminate processes- Do not kill sessions prematurely (`SKILL.md` Rules section).Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File type combined with upload actionopencode_acp_client.py:184 · File type combined with upload action — agent may exfiltrate local data filesself.log("Sending task...")Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Process kill commandSKILL.md:454 · Process kill command — agent can terminate processes7. **Be patient** - Don't kill sessions prematurelyFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedvenv_utils.py:76 · Python subprocess execution detectedcheck = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Process kill commandSKILL.md:85 · Process kill command — agent can terminate processesprocess action:kill sessionId:neat-zephyrFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedvenv_utils.py:132 · Python subprocess execution detectedsubprocess.run(python_for_venv + ["-m", "venv", str(venv_dir)], check=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05

Cost to the agent

Instructions loaded
≈4,374 tok
2 files · 9 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.