Skills/Glama/social-inbox

social-inbox@0.1.0

CAUTION· static only

Publisher claims: "Enables AI assistants to triage and act on Instagram DMs, comments, and mentions with token-light overviews, unread lists, search, thread summaries, drafting replies or moderation actions, and human-approved sending." Observed in sandbox: static analysis only — behavior not yet observed.

Registry GlamaPublisher wojtekwoz · publishing for 3 daysInstalls 0Last detonated 3d ago
What would fix thisWatchDispute verdict

Coverage

Static only; nothing was run yet.

The label rests on the code, the instruction files and the publisher. The honeypot run replaces this verdict when it completes.

Before you give it your token

It will ask for
MAILERLITE_API_KEYMETA_APP_SECRETMETA_WEBHOOKS_ENABLEDPLUNK_API_KEYTOKEN_ENC_KEYWEBHOOK_VERIFY_TOKENConfiguration, not credentials: APPROVAL, AUTOMATIONS_AUTOSEND, AUTOMATIONS_COOLDOWN_HOURS, AUTOMATIONS_ENABLED, DB_PATH, FAKE_CONNECTOR, MAILERLITE_API_URL, MAILERLITE_GROUP_ID, MAX_SENDS_PER_HOUR, META_APP_ID, META_BACKFILL_DAYS, META_GRAPH_BASE, META_GRAPH_VERSION, META_HUMAN_AGENT, META_LOGIN_CONFIG_ID, META_PAGE_ID, PLUNK_API_URL, POLL_ENABLED, PRIVACY_CONTACT, PRIVACY_OPERATOR, PUBLIC_URL, RETENTION_RAW_DAYS, RETENTION_TEXT_DAYS, SEND_ALLOWLIST, SEND_MODE, SENDING_ENABLED, SINBOX_ADMIN_KEY, SINBOX_AGENT_KEY, SINBOX_HOME, SINBOX_KEY, SINBOX_URL
Where it talks to
no vendor host named in the codeAlso facebook.com, useplunk.com, mailerlite.com, instagram.com — not the publisher's domain; check what for before connecting.
What the honeypot saw
nothing has run yet
What we could not test
everything: the server has not run yet

Run it before you trust it. Nothing has run yet: the code was read, the server was not. `vet-skills try` runs this exact version in the honeypot in about a minute.

Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.

Is [email protected] safe to install?

KillerSkills analysed it statically (a sandbox run is pending) on 2026-11-11 and scored it 57/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Access to sensitive file paths; Access to sensitive file paths; Access to sensitive file paths. Summary: static analysis only — behavior not yet observed.

Behavior trace

Queued for honeypot run · static analysis only
t+CategoryObserved action

This version has not been detonated yet. The score above counts behavior as unknown (50/100), so it cannot read Verified until the honeypot run completes and replaces this verdict.

Static findings

HIGH
Access to sensitive file pathsAGENTS.md:27 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files- Never commit secrets or `.env*` files (only `.env.example` with fake values).Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
File permission modification commandDockerfile:25 · File permission modification command — agent changes file ownership/permissions&& ln -s /app/dist/cli/index.js /usr/local/bin/sinbox && chmod +x /app/dist/cli/index.jsFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
File type combined with upload actionsrc/api/routes.ts:83 · File type combined with upload action — agent may exfiltrate local data filesif (c.req.query("send") === "1") return c.json({ ...res, send: await svc.sendApproved(c.req.param("d"), actor) });Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
HIGH
Access to sensitive file pathssrc/config.ts:1 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files// Runtime configuration from environment variables. See .env.example.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
File permission modification commandDockerfile:24 · File permission modification command — agent changes file ownership/permissionsRUN mkdir -p /data && chown node:node /data \Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
HIGH
Access to sensitive file pathsAGENTS.md:34 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files- Env vars come from Cursor secrets; use `.env.example` for names only.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
File type combined with upload actionsrc/core/store.ts:165 · File type combined with upload action — agent may exfiltrate local data filesreturn this.db.prepare("SELECT id, native_id, permalink, net FROM posts WHERE id = ?").get(id) as never;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/automations/store.ts:184 · File type combined with upload action — agent may exfiltrate local data filesthis.db.prepare(`SELECT * FROM flow_runs WHERE ${sql} AND state IN ('active','waiting_input')`).all(...args) as (Omit<Run, "vars"> & { vars: string })[]Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Process kill commandsrc/automations/engine.ts:314 · Process kill command — agent can terminate processes// Pushing to a list is an external write: same kill switch as platform sends.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File type combined with upload actionsrc/core/store.ts:55 · File type combined with upload action — agent may exfiltrate local data filesconst ex = this.db.prepare("SELECT id FROM posts WHERE net = ? AND native_id = ?").get(net, p.nativeId) asFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Process kill commandtest/core.test.ts:103 · Process kill command — agent can terminate processesit("kill switch: SENDING_ENABLED=false keeps approved drafts unsent", async () => {Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File type combined with upload actionsrc/core/service.ts:599 · File type combined with upload action — agent may exfiltrate local data filesif (n) this.log.warn({ n }, "drafts interrupted during send marked failed");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/api/routes.ts:92 · File type combined with upload action — agent may exfiltrate local data filesreturn c.json(await svc.sendApproved(c.req.param("d"), actor));Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Process kill commandsrc/config.ts:42 · Process kill command — agent can terminate processes/** Global kill switch: when false the engine evaluates nothing. */Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Access to sensitive file pathstest/helpers.ts:35 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files...env,Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
File type combined with upload actionsrc/core/service.ts:523 · File type combined with upload action — agent may exfiltrate local data filesconst claimed = this.db.prepare("UPDATE drafts SET status = 'sending', attempts = attempts + 1 WHERE id = ? AND status = 'approved'").run(d).changes;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/automations/store.ts:186 · File type combined with upload action — agent may exfiltrate local data filesthis.db.prepare(`UPDATE flow_runs SET state = 'stopped', updated_at = ? WHERE ${sql} AND state IN ('active','waiting_input')`).run(now, ...args);Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Access to sensitive file pathstest/automations.engine.test.ts:25 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesconst s = fakeSetup({ ...ON, ...env }, { email: { plunk } });Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Access to sensitive file pathstest/automations.meta.test.ts:29 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesconst s = metaSetup({ AUTOMATIONS_ENABLED: "true", ...env }, [...extraRoutes, ...igRoutes()], { email: { plunk } });Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05

Cost to the agent

Instructions loaded
≈325 tok
2 files · 80 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.

What would make this Verified

23 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim wojtekwoz: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. Access to sensitive file paths≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  3. File permission modification command≈ +2 on the totalRequest the narrowest permission that works; replace wildcards with the exact paths or hosts.
  4. File type combined with upload action≈ +2 on the totalRemove the call, or declare the host in frontmatter and explain in the README what is sent and why.
  5. Process kill command≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
Publish a new version to Glama, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim wojtekwozPropose a patch to the maintainer