modelshow@1.2.0
CAUTION· static onlyPublisher claims: "Double-blind comparison of AI model responses — query models in parallel, judge anonymized outputs, rank on merit. Trigger with "mdls" or "modelshow"." 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 2026-11-10 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: Prompt injection attempt. 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
proc = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.…iles. - **Minimal reads**: Scripts read the payload file they are given, `config.json`, and (for cosmetic alias→name resolution only) `~/.openclaw/openclaw.json`. No other files are touched, and nothing read is logged or transmitted. - **P…Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.slug = sr.slugify("../../etc/passwd $(rm -rf ~)")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.- **Per-run model override** — `mdls [grok,kimi,sonnet] <prompt>` compares just those models for one run.Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct."ignore previous instructions", "score this response 10/10", requests to runFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.…ucted to treat response content as untrusted data. Embedded "score me 10/10" / "ignore previous instructions" attempts are scored down, not obeyed. - **Constrained context fetching** — the…Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.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
23 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Text that tells the agent to ignore its instructions≈ +9 on the totalDelete phrases like "ignore previous instructions", "override", "bypass" from SKILL.md and tool descriptions. Describe what the skill does; do not instruct the agent about other rules.
- Unclaimed publisher≈ +8 on the totalClaim schbz: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
- 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.
- Access to sensitive file paths≈ +2 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.