Is browse-awesome-skills safe to install?

SaferSkills independently audited browse-awesome-skills (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.

CategoryWeightCategory scoreContribution

Securityprompt, exec, net, exfil, eval

35%

100

35.0 pts

Supply chainhash, typosquat, maintainer, lockfile

20%

100

20.0 pts

Maintenancestaleness, pinning, CI

15%

100

15.0 pts

TransparencySKILL.md, perms, README

15%

100

15.0 pts

Communityinstalls, verify, response

15%

100

15.0 pts

Findings & checks · 0 flagged

Securityscore 100 · 0 findings

✓—All security checks passedNo findings in this category for the latest scan.pass

Supply chainscore 100 · 0 findings

✓—All supply chain checks passedNo findings in this category for the latest scan.pass

Maintenancescore 100 · 0 findings

✓—All maintenance checks passedNo findings in this category for the latest scan.pass

Transparencyscore 100 · 0 findings

✓—All transparency checks passedNo findings in this category for the latest scan.pass

Communityscore 100 · 0 findings

✓—All community checks passedNo findings in this category for the latest scan.pass

The primary manifest — the file an agent reads to learn what this artifact does.

skills/browse-awesome-skills/SKILL.md · 1 file

skills/browse-awesome-skills/SKILL.md1.7 KB · Markdown

name: browse-awesome-skills

description: Searches the Awesome Claude Skills list to suggest skills, collections, authoring tools, or docs matching the user's need. Use when the user asks where to find a skill for a specific task, which collection is worth installing, or what the official Anthropic resources are.

allowed-tools: WebFetch

Browse Awesome Skills

Help the user find the right entry in the Awesome Claude Skills list.

Steps

Fetch the latest list: https://raw.githubusercontent.com/horiastanxd/awesome-claude-skills/main/README.md
Read the user's request and figure out which section(s) apply: Official, Collections, Individual skills, Authoring tools, Reading & docs, or Related.
Suggest 1-3 entries that fit. For each, give the link and the one-line description from the list verbatim.
If nothing fits, say so. Don't invent entries.

Guidelines

Quote descriptions from the list verbatim; don't rewrite them.
When recommending from Collections, mention whether the list is Claude-focused or multi-agent - that distinction is in the list itself.
If the user wants to author a new skill, point to skill-creator first unless they need something more specific.
If the request is about MCP servers or Claude Code plugins generally (not skills), point to the Related section, which cross-links to awesome-mcp-servers and awesome-claude-code.
Link the section anchor when useful, e.g. https://github.com/horiastanxd/awesome-claude-skills#collections.

Source

This skill is published alongside the list at https://github.com/horiastanxd/awesome-claude-skills. To add or correct an entry, open a PR there.

browse-awesome-skills— agent skill

Is browse-awesome-skills safe to install?

Browse Awesome Skills

Steps

Guidelines

Source

Audit the pieces. Scan the whole. Decide.