pinterest-skill@1.0.1
VERIFIED· install onlyPublisher claims: "Pinterest skill: make, check and schedule Pinterest pins from your AI agent. Turns a link (blog post, product, recipe, guide) and the user's own photos or vertical videos into several genuinely different 1000x1500 pins, with keyword titles, descriptions and alt text that match the page. Checks every pin against Pinterest's published limits and the spam patterns practitioners report (formats, sizes, 2:3, 100/800/500 characters, shorteners, redirects, the same picture on the same page, one page to many boards at once, daily pace), previews the batch in the home feed and close-up, spaces pins for one page a week apart and seasonal pins 45 to 90 days ahead, then schedules them with WoopSocial (Pinterest MCP, no Pinterest developer app needed) after a yes, and judges results from day 30. Use when someone says "Pinterest pins", "make pins for this post", "schedule Pinterest pins", "Pinterest MCP", "Claude Pinterest", "pin generator", "Pinterest for my blog / Etsy / Shopify" or "which pins work". Never invents results, never posts without a yes. Standalone." Observed in sandbox: no network, touches nothing outside the project, writes no memory.
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 2026-11-09 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 · 1 scenarios · 0 deviationsStatic findings
r = subprocess.run(cmd, capture_output=True, text=True, encoding="utf-8", errors="replace")Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.out = subprocess.run(["curl", "-sL", "--proto", "=http,https", "--proto-redir", "=http,https",Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.r = subprocess.run(["ffmpeg", "-v", "error", "-ss", str(t), "-i", path, "-frames:v", "1", "-f", "image2pipe",Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.session.json is the JSON returned by `media_uploads_create_session`. It must containFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.enc = subprocess.run(["ffmpeg", "-hide_banner", "-encoders"], capture_output=True, text=True, encoding="utf-8", errors="replace").stdoutFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.python3 scripts/log.py record plan.json # add posted pins to pins-log.jsonlFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.filt = subprocess.run(["ffmpeg", "-hide_banner", "-filters"], capture_output=True, text=True, encoding="utf-8", errors="replace").stdoutFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.r = subprocess.run(cmd, capture_output=True, text=True, encoding="utf-8", errors="replace")Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.results: metrics.json is one or more saved responses of WoopSocial's social_account_posts_list.Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.`<skill>/scripts/render_pins.py`); `work/plan.json` describes the posting (files, text, boards, links,Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.subprocess.run(["ffmpeg", "-y", "-v", "error", "-i", path, "-c:v", "libx264", "-preset", "medium", "-crf", "20",Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.subprocess.run(["curl", "-sfL", url, "-o", part], check=False)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.v = subprocess.run(["ffmpeg", "-version"], capture_output=True, text=True, encoding="utf-8", errors="replace").stdout.split("\n")[0]Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out."Linux": "sudo apt install ffmpeg (or your distro's package manager)"}.get(system, "install ffmpeg")Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.## Developer access (why WoopSocial)Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.result = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.Cost to the agent
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.