Skills/ClawHub/checkmate

checkmate@2.0.4

VERIFIED· install only

Publisher claims: "Enforces task completion: turns your goal into pass/fail criteria, runs a worker, judges the output, feeds back what's missing, and loops until every criteri..." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher insipidpoint · publishing for 269 daysInstalls 2,262Last detonated 37 min ago
$clawhub install checkmate
WatchReport an issue

Coverage

Bundled scripts ran with no arguments; no agent task scenario for this bundle.
Tested
2 of 2 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 2026-11-18 and scored it 84/100 (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 · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessbundled script run in the sandbox with no arguments
0.1sprocessexited 2: run.py: error: the following arguments are required: --workspace
0.1sprocessbundled script run in the sandbox with no arguments
0.1sprocessexec /usr/bin/mkdir
0.1sprocessexec /usr/bin/cat
0.1sprocessexec /usr/bin/touch
0.1sprocess2 of 2 bundled scripts run with no arguments
0.1sprocessscript backend runs setup only
0.1sprocessscript backend runs setup only
0.1sprocessno install scripts to re-run

Static findings

CRITICAL
Fake instruction boundary tagSKILL.md:99 · Fake instruction boundary tagopenclaw agent --session-id <isolated-id> --message <prompt> --timeout <N> --jsonFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Python subprocess execution detectedscripts/run.py:67 · Python subprocess execution detectedresult = subprocess.run(cmd, capture_output=True, text=True, timeout=timeout_s + 30)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Agent configured for autonomous execution without human approvalSKILL.md:132 · Agent configured for autonomous execution without human approvalAdd `--no-interactive` for fully autonomous runs (no user checkpoints).Fix: Declare and request only the permissions the task needs.
AST02
MEDIUM
File type combined with upload actionSKILL.md:95 · File type combined with upload action — agent may exfiltrate local data filesThe main agent acts as the bridge: when `pending-input.json` exists and the user replies, the agent writes their response to `user-input.md`. The orchestrator picks it up automatically.Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Python subprocess execution detectedscripts/run.py:132 · Python subprocess execution detectedresult = subprocess.run(cmd, capture_output=True, text=True, timeout=timeout_s + 10)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
File type combined with upload actionSKILL.md:196 · File type combined with upload action — agent may exfiltrate local data files…ript is interrupted, just re-run it with the same `--workspace`. It reads `state.json` and skips completed steps. Locked `criteria.md` is reused; completed `iter-N/output.md` files are not re-run. ## Prompts Active prompts called by `run.p…Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Python subprocess execution detectedscripts/run.py:106 · Python subprocess execution detectedresult = subprocess.run(cmd, capture_output=True, text=True, timeout=30)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
File type combined with upload actionSKILL.md:136 · File type combined with upload action — agent may exfiltrate local data files5. **Bridge user replies**: When user responds to a checkpoint message, check for `pending-input.json` and write their response to `workspace/user-input.md`.Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07

Cost to the agent

Instructions loaded
≈2,395 tok
1 file · 10 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.

checkmate@2.0.4 safety verdict: Verified (install only) — KillerSkills