Skill/Static safety grade

skills/skills-folders/whatsapp-mgv

github/aztr0nutzs/NET_NiNjA.v1.2#skills/skills-folders/whatsapp-mgv

litmus-skill-v3 · 2026-07-05

graded at commit 91f16c5 · 2026-02-06

The skills/skills-folders/whatsapp-mgv skill is graded D by polygraph under litmus-skill-v3, as of 2026-07-05, anchored to its content hash.

Graded under litmus-skill-v3; the current skill methodology is litmus-skill-v2. A re-run may change the grade.

Self-reported “Use when you need to control WhatsApp from Clawdbot via the whatsapp tool, including sending messages, managing chats, and handling media in WhatsApp conversations.” — the skill’s own SKILL.md description at the graded commit, not part of the grade.

A static safety grade — a deterministic scan of the skill’s SKILL.md and bundled files. An A means static-clean, not behavioral proof: a skill’s instructions are interpreted by an agent at runtime.

Share on X

S-01 Prompt-injection / context-poisoningpass

S-03 Data-exfiltration instructionspass

S-04 Dangerous bundled commandsfail

dangerous-command· high· SKILL.md
base64 -D | bash
dangerous-command· high· SKILL.md
base64-decoded: bash -c "$(curl

content hash · 0xfeb865edae…7f7f

How to fix this →

Guided remediation — the specific changes that clear this grade.

Source · github.com/aztr0nutzs/NET_NiNjA.v1.2/tree/main/skills/skills-folders/whatsapp-mgv

Watch for changes

This grade is a snapshot of the skill’s files at one commit. Get an email when a new commit changes skills/skills-folders/whatsapp-mgv and polygraph re-runs the litmus — one message per change, one-click unsubscribe.

Monitor this skill

Reproduce this grade

The skill litmus is open and deterministic. Point it at the skill directory and compare the grade and content hash — a false grade is falsifiable, not merely disputable.

npx -p @polygraphso/litmus polygraphso-litmus-skill <skill-dir>

Embed this badge

Drop it in the skill’s README, docs, or listing. It always shows the current grade and links back here.

Markdown — badge

[![polygraph](https://www.polygraph.so/api/badge/skill?skill=github/aztr0nutzs/NET_NiNjA.v1.2/skills/skills-folders/whatsapp-mgv)](https://www.polygraph.so/skill/github/aztr0nutzs/NET_NiNjA.v1.2/skills/skills-folders/whatsapp-mgv)

HTML — badge

<a href="https://www.polygraph.so/skill/github/aztr0nutzs/NET_NiNjA.v1.2/skills/skills-folders/whatsapp-mgv"><img src="https://www.polygraph.so/api/badge/skill?skill=github/aztr0nutzs/NET_NiNjA.v1.2/skills/skills-folders/whatsapp-mgv" alt="polygraph grade"></a>

Markdown — card

[![polygraph](https://www.polygraph.so/api/badge/skill/card?skill=github/aztr0nutzs/NET_NiNjA.v1.2/skills/skills-folders/whatsapp-mgv)](https://www.polygraph.so/skill/github/aztr0nutzs/NET_NiNjA.v1.2/skills/skills-folders/whatsapp-mgv)

Questions

What does the D skill grade mean for skills/skills-folders/whatsapp-mgv?: It’s a static safety grade(A/B/D/F) from a deterministic scan of the skill’s SKILL.md and bundled files. An A means static-clean — not behavioral proof, since a skill’s instructions are interpreted by an agent at runtime.
What did polygraph check?: Three static checks: S-01 prompt-injection and context-poisoning, S-03 data-exfiltration instructions, and S-04 dangerous bundled commands. The full battery is in the methodology.
How do I reproduce this grade?: Run npx -p @polygraphso/litmus polygraphso-litmus-skill <skill-dir>. The scan is open and deterministic, anchored to the skill’s content hash, so the same directory yields the same grade.