llmfit-hardware-model-matcher
https://raw.githubusercontent.com/aradotso/trending-skills/main/skills/llmfit-hardware-model-matcher/SKILL.md
github.com/aradotso/trending-skills
Scanned Thu, 28 May 2026 17:11:42 GMT
Scan ID crawl-gweoo21talr9iuokfot9vrab · 8ms
B
SCORE 75 / 100
Verdict: Safe to install

2 high-severity findings.

This skill runs unsafe shell commands plus 4 other issues listed below.

0 critical2 high3 medium7 rules passed

Why grade B?

score · 75 / 100

The current grade reflects 2 high-severity findings (any HIGH → B).

0 CRIT2 HIGH3 MED0 LOW
To reach a higher grade
  • A
    Reach Atarget score 95

    Resolve all 2 HIGH + 1 of 3 MED (cap is 2).

Thresholds are documented at /docs/grading. Source-of-truth is the grade() function in @skillox/scanner.

Findings · ordered by severity

high
Dangerous shell pattern: curl | shell
The skill contains a shell command pattern (`curl | shell`) commonly used in destructive or supply-chain attacks.
rule: dangerous-shellline: 32CWE-78
▾
30### Quick install script
31```sh
32curl -fsSL https://llmfit.axjns.dev/install.sh | sh← curl | shell — common in destructive or supply-chain attacks
33
34# Without sudo, installs to ~/.local/bin
high
Dangerous shell pattern: curl | shell
The skill contains a shell command pattern (`curl | shell`) commonly used in destructive or supply-chain attacks.
rule: dangerous-shellline: 35CWE-78
▾
33
34# Without sudo, installs to ~/.local/bin
35curl -fsSL https://llmfit.axjns.dev/install.sh | sh -s -- --local← curl | shell — common in destructive or supply-chain attacks
36```
37
med
Arbitrary subprocess execution detected
The skill spawns subprocesses. Without a capability manifest declaring this, the skill could execute arbitrary commands.
rule: subprocess-executionline: 299CWE-78
▾
297def get_best_model_for_task(use_case: str, min_fit: str = "good") -> dict:
298 """Use llmfit to select the best model for a given task."""
299 result = subprocess.run(← spawns a subprocess outside declared capabilities
300 ["llmfit", "recommend", "--json", "--use-case", use_case, "--limit", "1"],
301 capture_output=True,
med
Arbitrary subprocess execution detected
The skill spawns subprocesses. Without a capability manifest declaring this, the skill could execute arbitrary commands.
rule: subprocess-executionline: 310CWE-78
▾
308def plan_hardware_requirements(model_name: str, context: int = 4096) -> dict:
309 """Get hardware requirements for running a specific model."""
310 result = subprocess.run(← spawns a subprocess outside declared capabilities
311 ["llmfit", "plan", model_name, "--context", str(context), "--json"],
312 capture_output=True,
med
No capability manifest declared
The skill ships without a `manifest.yaml` or `capabilities` block in its frontmatter. Without a manifest, the runtime cannot enforce what this skill is permitted to do.
rule: no-manifest
▾
Scan another →Share
skillox.io/r/crawl-gweoo21talr9iuokfot9vrab