skill-router-skills

github.com/legendtkl/agentic-skill-router
Verdict: Generally safe
0 critical1 high1 medium
B
SCORE 75 / 100
$skillox install skill-router-skillsSoon
Sign in to followFollowing emails you when a re-scan drops the grade. Opt-out is per-creator on /account/billing.

Why grade B?

score · 75 / 100

The current grade reflects 1 high-severity finding (any HIGH → B).

0 CRIT1 HIGH1 MED0 LOW
To reach a higher grade
  • A
    Reach Atarget score 95

    Resolve all 1 HIGH.

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

Latest scan findings

Scan crawl-uh4kgazbuexaewmjkk0xjn05 · Thu, 28 May 2026 15:18:16 GMT · 1ms

high
Obfuscation pattern: base64 blob
The skill contains an obfuscated payload pattern. Legitimate skills rarely include long base64/hex/unicode-escaped runs; review the content carefully.
rule: obfuscationline: 3CWE-506
▾
1---
2name: skill-router-skills
3description: MUST be used FIRST, before any other tool, for EVERY user request that mentions a specific tool, API, file format, service, framework, library, CLI, platform, dataset, or domain workflow -- e.g. parsing/operating/querying/configuring/deploying/transcribing/analyzing/debugging/generating/refactoring/troubleshooting a named technology. A large catalog of disabled Agent Skills is installed locally; one of them likely specializes in this exact task. Invoke this skill FIRST to identify which one before attempting the task.← base64 blob — review for hidden payload
4metadata:
5 skill-router.version: "1"
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
▾
View latest scan →
skillox.io/c/skill-router-skills