hermesone
github/BankrBot/skills#hermesone
litmus-skill-v2 · 2026-06-25
graded at commit 9234164 · 2026-06-23
The hermesone skill is graded A by polygraph under litmus-skill-v2, as of 2026-06-25, anchored to its content hash.
Self-reported “Install, update, and manage the Hermes One desktop app via the `hermesone` npm package. Use when a user wants to set up Hermes One, install or upgrade it from the command line, check the installed version, preview a release before installing, pin a specific version, or drive…” — 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.
no bundled executable scripts
content hash · 0xb7341e612d…3c76
Source · github.com/BankrBot/skills/tree/main/hermesone
Watch for changes
This grade is a snapshot of the skill’s files at one commit. Get an email when a new commit changes hermesone and polygraph re-runs the litmus — one message per change, one-click unsubscribe.
Monitor this skillReproduce 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.
[](https://www.polygraph.so/skill/github/BankrBot/skills/hermesone)<a href="https://www.polygraph.so/skill/github/BankrBot/skills/hermesone"><img src="https://www.polygraph.so/api/badge/skill?skill=github/BankrBot/skills/hermesone" alt="polygraph grade"></a>[](https://www.polygraph.so/skill/github/BankrBot/skills/hermesone)Questions
- What does the A skill grade mean for hermesone?
- It’s a static safety grade(A/B/D/F) from a deterministic scan of the skill’s
SKILL.mdand 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.