avenir-web@1.0.1
CAUTION· install onlyPublisher claims: "Execute and improve Avenir-Web autonomous web tasks end-to-end with mode selection, instruction validation, single or batch runs, and next-step recommendations." Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Bundled scripts ran with no arguments; no agent task scenario for this bundle.- Tested
- 8 of 27 bundled scripts run with no arguments (the rest were not run: per-bundle cap), 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 2026-11-20 and scored it 75/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: OS command execution function call detected; Fake instruction boundary tag; Auto-update or dynamic fetch configuration. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 1 s · 2 scenarios · 0 deviationsStatic findings
os.system(" ".join(["cp", str(config), str(save_file)]))Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.bad = ["/graphql", "/api/", "/api", "/v1/", "/v2/", "/v3/", "/rest/", ".json", ".csv", ".xml", "?format=json", "output=json"]Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.python example.py --task "<instruction>" --website "<url>" --mode headlessFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.self.logger.info(f"Checklist auto-update (atomic): {item_id} -> {new_status} ({reason})")Fix: Pin versions and sources; vendor anything fetched at install time."Set OPENROUTER_API_KEY in the process environment (or .env)."Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.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
5 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- OS command execution function call detected≈ +9 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
- Unclaimed publisher≈ +8 on the totalClaim yiliu-li: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- Auto-update or dynamic fetch configuration≈ +4 on the totalPin versions and sources; vendor anything fetched at install time.
- 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.
- File type combined with upload action≈ +2 on the totalPut hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.