agentsclimarketplace

Check artifact reputation

Skill gaelic-ghost/socket/plugins/cybersecurity-skills/skills/check-artifact-reputation

The Source for macOS Agent Workflows

Install
npx -y skills add gaelic-ghost/socket --skill check-artifact-reputation

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 6 stars6 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Check local and external reputation for a suspicious artifact, signer, hash, URL, domain, certificate, package, or vendor. Use when provenance and threat-intelligence context could inform triage, while sample-upload privacy, stale intelligence, hash-only misses, false positives, and reputation-versus-behavior limits must remain explicit.

SKILL.md

2.0 KB, 315 tokens by cl100k_base, as published. Nobody here has run it

Check Artifact Reputation

Overview

Gather provenance and intelligence without treating popularity, valid signing, a clean lookup, or a vendor label as a safety verdict. Prefer local identity and vendor sources before sending data to third parties.

Read references/reputation-evidence.md for source ordering and interpretation.

Workflow

  1. Fix identity.

    • Record artifact hashes, signer/certificate, exact version, source URL, domain, resolved destinations, and acquisition time.

  2. Check local evidence.

    • Inspect quarantine/provenance, signature/notarization, known installation records, local security detections, and expected vendor distribution paths.

  3. Check authoritative sources.

    • Prefer vendor advisories, release checksums/signatures, certificate status, official repositories, and current platform security sources.
    • Date each lookup.

  4. Decide whether external intelligence is appropriate.

    • Explain whether the service receives only a hash/domain or may upload/retain the artifact.
    • Obtain explicit approval before sending private artifacts, URLs, customer data, or unknown binaries.

  5. Correlate results.

    • Record detection names, engines/sources, first/last seen, submission context, prevalence, relations, and conflicting classifications.
    • Distinguish “not present” from “known benign.”

  6. Feed behavior analysis.

    • Use reputation to prioritize static/dynamic checks, not replace them.

Output

Return identity, sources/date, privacy decision, reputation observations, conflicts, interpretation limits, confidence effect, and next behavioral check.

What ships with it: 2 files

1.2 KB alongside SKILL.md

agents/

references/

Gives 0 of the 12 instructions most quality gates skills give in 315 tokens

Counted across 1,195 of the 2,094 authors here whose files we hold, read 2026-08-07

  • Read the output and check the exit codein 54 of 1195, across 14 files
  • Verify requirements using a line-by-line checklistin 53 of 1195, across 12 files
  • Identify the verification command proving the claimin 51 of 1195, across 12 files
  • Run the full verification commandin 50 of 1195, across 11 files
  • Verify output confirms the claimin 49 of 1195, across 12 files
  • Check version control diff after agent delegationin 46 of 1195, across 6 files
  • State claim with evidencein 44 of 1195, across 4 files
  • Run the test suitein 33 of 1195, across 26 files
  • Keep state in memory by defaultin 27 of 1195, across 6 files
  • Make prototype runnable with one commandin 26 of 1195, across 5 files
  • Produce a verification reportin 25 of 1195, across 14 files
  • Detect the package manager from lockfilesin 24 of 1195, across 5 files

Said here and by no other author read

  • fix the artifact identity
  • check local evidence first
  • date each external lookup
  • explain external service data privacy exposure
  • obtain explicit approval before uploading private artifacts
  • correlate reputation results

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 326,984. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.