Skills/npm/spine-rigc

spine-rigc@3.6.0

VERIFIED· install only

Publisher claims: "AI-authored 2D rigging and animation, verified before it is written. rigc compiles a rig spec into skeleton data in the Spine 4.3 format, gates it with named assertions held to a spine-core round trip's verdicts, and emits nothing that fails. Ships as an " Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry npm (MCP server)Publisher rig-c · publishing for 77 daysInstalls 19,022Last detonated 8 h ago
$claude mcp add spine-rigc -- npx -y spine-rigc
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 2026-11-08 and scored it 87/100 (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

HIGH
Destructive file system command detectedsrc/cli/shared.ts:1099 · Destructive file system command detected…png` stay over opaque `BACKGROUND` unchanged', 'sheet-format': `the table format \`render --sheet\` writes beside each sheet page (default \`${DEFAULT_SHEET_FORMA…Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File type combined with upload actionsrc/cli/repack.ts:458 · File type combined with upload action — agent may exfiltrate local data files" .. check (b) skeleton.json: byte-identical to the input's — the pack owns none of it" +Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actionsrc/cli/shared.ts:1269 · File type combined with upload action — agent may exfiltrate local data files'write the repack even where the rebuilt skeleton.json differs from the input\'s, and print every differing path ' +Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actionsrc/cli/repack.ts:347 · File type combined with upload action — agent may exfiltrate local data filesconsole.log(`rigc repack ${input.skeletonPath}`);Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actionsrc/cli/repack.ts:19 · File type combined with upload action — agent may exfiltrate local data files* (b) the rebuilt `skeleton.json` is byte-identical to the input's. A repackFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actionsrc/cli/shared.ts:1481 · File type combined with upload action — agent may exfiltrate local data files'skeleton.atlas, skeleton.model.json and the pages --pack or --copy-images put in',Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actionsrc/cli/repack.ts:348 · File type combined with upload action — agent may exfiltrate local data filesconsole.log(` .. atlas ${input.atlasPath}`);Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actionsrc/cli/repack.ts:466 · File type combined with upload action — agent may exfiltrate local data filesconsole.log(` .. check (b) ${head}, accepted by --${ACCEPT_FLAG} — the output's skeleton is this rigc's rebuild, not the input's bytes:`);Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actionsrc/cli/shared.ts:1574 · File type combined with upload action — agent may exfiltrate local data files'skeleton.json is byte-identical to the input\'s — the pack owns the atlas and the pages',Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actionsrc/cli/shared.ts:1539 · File type combined with upload action — agent may exfiltrate local data files'skeleton.json is byte-identical to the input\'s — the pack owns the atlas and the pages',Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actionsrc/cli/shared.ts:1588 · File type combined with upload action — agent may exfiltrate local data files'skeleton.json is byte-identical to the input\'s, so spine.sha256 names the file on disk',Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actionsrc/deformbuild.ts:24 · File type combined with upload action — agent may exfiltrate local data files/** The model document (`skeleton.model.json`), or `null` when the input carries none (a Spine export). */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
≈89 tok
1 file · 81 in bundle

Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.

Known vulnerabilities

No advisories in OSV for spine-rigc@3.6.0 as of 6 h ago. This is the package itself, not its dependencies.

spine-rigc@3.6.0 safety verdict: Verified 87/100 — KillerSkills