secure-1pass-access
Skill153 starsChanged 44 days agoMITView on GitHub
Let the agent access local 1pass CLI credentials, without compromising security standards
- Installs packages
In this repository41 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- .github/copilot-instructions.mdCopilot instructions
- broken-access-controlSkill
- cdn-peekSkill
- http-request-smugglingSkill
- jwt-attacksSkill
- ssrf-oobSkill
- webapp-probeSkill
- blockchain-forensicsSkill
- foundry-pocSkill
- safe-huntSkill
- smart-contract-auditSkill
- cloud-bucket-bruteSkill
- infrastructure-auditSkill
- dylib-hijack-scanSkill
- endpoint-threat-huntSkill
- parse-securitySkill
- agentic-seoSkill
- agent-onboardingSkill
- context-window-to-skillSkill
- git-commitSkill
- keen-eyesSkill
- no-aispeakSkill
- self-improveSkill
- shadow-partnerSkill
- training-guideSkill
- variant-tableSkill
- auditor-quizSkill
- audit-scopeSkill
- evidence-captureSkill
- external-enumerationSkill
- gdocs-audit-reportSkill
- hackerone-reportSkill
- nuclei-suggestSkill
- pre-bountySkill
- sandboxed-audit-runnerSkill
- tiny-auditorSkill
- vm-labSkill
- llm-fuzz-toolsSkill
- mcp-server-pentestSkill
- prompt-injection-auditSkill
The file
Files
1Password CLI (op) lets you access secrets and manage your account from your terminal and scripts. Install via brew install 1password-cli or winget install 1password-cli.
When an agent is given access to 1pass it needs to only read what the user wants, although the user don't necessarily know all details. to make the search seamless for the user we confirm that we know the account, and vault he wants to get the data from.
It could be that the item in the vault isn't accurate or it's multiple items, in which case we want to suggest a search query to then use via the op cli to match all at once and store them for the session only. this is because everytime we access a read 1password auto-opens a prompt requiring a fingerprint to access, which can be annoying if requested a lot.
Due to above we really prefer to do a 1-shot retreival for the entire session's purposes, to not depend on the user more than this 1/2 call.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.