Skills/ClawHub/run-workflow-weaver

run-workflow-weaver@0.1.5

VERIFIED· install only

Publisher claims: "Drives the hosted Workflow Weaver service (weaver.vibingfun.com) through its workflow-weaver CLI and MCP server: create projects, upload API doc sources (OpenAPI specs, endpoint lists, code snippets), generate step-by-step workflow guides on the service, and export them as Markdown, SVG, PNG, PDF or JSON. Generation happens server-side and needs a Workflow Weaver account. Bundled smoke.sh checks that the CLI and MCP server are installed and authenticated and, when a token is set, reads the account's billing status (plan and quota, read-only). Use when the user asks to use Workflow Weaver or to turn their API docs into a Workflow Weaver guide; not for general diagramming or documentation requests." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher britrik · publishing for 172 daysInstalls 602Last detonated 23 min ago
$clawhub install run-workflow-weaver
WatchReport an issue

Coverage

Bundled scripts ran with no arguments; no agent task scenario for this bundle.
Tested
1 of 1 bundled script 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

What changed since 0.1.2

vet-skills diff run-workflow-weaver 0.1.2 0.1.5

In the sandbox, this version reached for nothing 0.1.2 did not. Compared from the two recorded runs, not from source.

0.1.2 was not run in the sandbox (static only); the comparison covers what static analysis recorded only.

The guard can hold an update like this until someone approves it (runtime.on_change: hold). A change that only shows with a real credential, or on a path the run did not reach, is not in a trace and so not in this comparison.

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 86/100 (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
0.0sprocessexec /usr/bin/rm
0.0sprocessexited 1:
0.0sprocess1 of 1 bundled script run with no arguments
0.0sprocessscript backend runs setup only
0.0sprocessscript backend runs setup only
0.1sprocessno install scripts to re-run

Static findings

MEDIUM
File permission modification commandSKILL.md:61 · File permission modification command — agent changes file ownership/permissions| Config file path | `~/.workflow-weaver/config.json` (chmod 600) — document but never read directly in automation scripts; one-time setup extraction is acceptable |Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
File permission modification commandSKILL.md:48 · File permission modification command — agent changes file ownership/permissionsAfter an interactive login the CLI stores the refresh token in `~/.workflow-weaver/config.json` (chmod 600) and uses it from there, so a local agent needs nothing else.Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
File permission modification commandSKILL.md:149 · File permission modification command — agent changes file ownership/permissions…se the user-level config (not a project file that could be committed), keep it `chmod 600`, and revoke the token from your Workflow Weaver account if the file leaks. …Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
npx invocation of non-well-known packageSKILL.md:149 · npx invocation of non-well-known package — may execute untrusted code…es run the globally installed, pinned `workflow-weaver-mcp` binary rather than `npx ...@latest`. Hosts that cannot read your shell environment store these values in their confi…Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Process kill commandsmoke.sh:133 · Process kill command — agent can terminate processesif ! kill -0 "$MCP_PID" 2>/dev/null; thenFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandsmoke.sh:145 · Process kill command — agent can terminate processeskill "$MCP_PID" 2>/dev/null || trueFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandsmoke.sh:147 · Process kill command — agent can terminate processeskill -0 "$MCP_PID" 2>/dev/null && kill -9 "$MCP_PID" 2>/dev/null || trueFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandsmoke.sh:20 · Process kill command — agent can terminate processeskill $pids 2>/dev/null || trueFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05

Cost to the agent

Instructions loaded
≈2,681 tok
1 file · 3 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.