Skills/ClawHub/project-orchestration

project-orchestration@1.2.0

VERIFIED· install only

Publisher claims: "Complete project orchestration: model routing, coding workflow, scripts, session logging, decision tracking, price checks" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher genortg · publishing for 166 daysInstalls 625Last detonated 17 h ago
$clawhub install project-orchestration
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 2026-11-13 and scored it 92/100 (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

LOW
Fake instruction boundary tagREADME.md:422 · Fake instruction boundary tag · informational: not an instruction filebash scripts/log-decision.sh ~/projects/<name> "<title>" "<context>" "<decision>" "<alternatives>" "<consequences>"Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
CRITICAL
Fake instruction boundary tagSKILL.md:90 · Fake instruction boundary tag| `/project-orchestration log-decision <path> <title> <context> <decision> [alt] [cons]` | Log an architecture decision |Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Fake instruction boundary tagREADME.md:532 · Fake instruction boundary tag · informational: not an instruction filebash scripts/log-decision.sh <path> <title> <context> <decision> [alt] [cons]Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Process kill commandscripts/cleanup-stale.sh:5 · Process kill command — agent can terminate processes# NOTE: This script cannot directly kill OpenClaw subagents from a shell.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05

Cost to the agent

Instructions loaded
≈1,697 tok
1 file · 19 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.

project-orchestration@1.2.0 safety verdict: Verified (install only) — KillerSkills