grazer-skill-main@1.0.0
CAUTION· static onlyPublisher claims: "Enable AI agents to discover, filter, and engage with content across 24 platforms including social, academic, and decentralized networks with auto-generated..." Observed in sandbox: static analysis only — behavior not yet observed.
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.
Is [email protected] safe to install?
KillerSkills analysed it statically (a sandbox run is pending) on 2026-11-07 and scored it 53/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: HTML comment carrying imperative instructions to the agent; HTML comment carrying imperative instructions to the agent; Outbound HTTP to raw IP address. Summary: static analysis only — behavior not yet observed.
Behavior trace
Queued for honeypot run · static analysis onlyThis 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
node-url: https://50.28.86.131Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.node-url: https://50.28.86.131Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls."llm_url": "http://100.75.100.89:8080/v1/chat/completions",Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.mock_resp.json.return_value = {"posts": [SAMPLE_BSKY_POST]}Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.console.log(` ✓ Moltbook: ${filteredPosts.length} quality posts (from ${allContent.moltbook.length})`);Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.console.log('\n🦞 Clawsta Posts:\n');Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.e.g., 1.8.0 (run grazer --version)Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.chmod +x "/tmp/${PKG}/usr/bin/grazer"Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.console.log('\n📚 Moltbook Posts:\n');Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.console.log('\n🏛️ The Colony Posts:\n');Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.return resp.json().get("posts", [])Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.e.g., v20.10.0 (run node --version)Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.console.log('\n⚡ MoltX Posts:\n');Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.- **API keys in local config only** — keys read from `~/.grazer/config.json` (chmod 600)Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.llm_url: str = "http://100.75.100.89:8080/v1/chat/completions",Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.mock_resp.json.return_value = {"posts": [SAMPLE_BSKY_POST]}Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.mock_resp.json.return_value = {"feed": [{"post": SAMPLE_BSKY_POST}]}Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why."llm_url": "http://100.75.100.89:8080/v1/chat/completions",Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.llm_url: str = "http://100.75.100.89:8080/v1/chat/completions",Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.## 7. Update CLAUDE.mdFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.console.log(` [${p.post_type || 'post'}] by ${author} | ${p.comment_count || 0} comments\n`);Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.Add to `/home/scott/CLAUDE.md`:Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.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.
What would make this Verified
27 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Unclaimed publisher≈ +8 on the totalClaim papyrusssssss: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- Hidden instructions≈ +6 on the totalRemove HTML comments, zero-width characters and white-on-white text that carry instructions. Everything the agent is meant to read should be visible to the person reading the file.
- URL using raw IP address≈ +2 on the totalReplace encoded or assembled strings with plain literals and remove undeclared network calls.
- Outbound HTTP to raw IP address≈ +2 on the totalReplace encoded or assembled strings with plain literals and remove undeclared network calls.
- 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.
- File permission modification command≈ +2 on the totalRequest the narrowest permission that works; replace wildcards with the exact paths or hosts.