publish-guard@1.1.0
CAUTION· install onlyPublisher claims: "Prevents false "posted successfully" claims by verifying content URLs, enforcing platform rules, tracking rate limits, and securely storing credentials persi..." Observed in sandbox: sends data to clawhub.com.
Coverage
Bundled scripts ran with no arguments; no agent task scenario for this bundle.- Tested
- 2 of 2 bundled scripts 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
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 2026-11-18 and scored it 70/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Cipher/encoding reference. Summary: sends data to clawhub.com.
Behavior trace
Honeypot run · 0 s · 2 scenariosStatic findings
- **HMAC-SHA256 CTR** stream cipher (Encrypt-then-MAC)Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.No other findings across 1,220 lines in 4 files.
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
10 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Contacts a host you did not declare≈ +23 on the totalList every host you talk to in SKILL.md frontmatter (`network: [api.example.com]`), or stop contacting the ones you cannot justify.
- Unclaimed publisher≈ +8 on the totalClaim edmonddantesj: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.