Secure secrets for agents
Skill sarveshsea/design-skills/skills/secure-secrets-for-agents
Practical design judgment for AI coding agents: 78 installable skills for craft, research, generation, Figma, and Memoire.
npx -y skills add sarveshsea/design-skills --skill secure-secrets-for-agentsAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 6 stars6 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Handle agent credentials with env refs, redaction, least privilege, and non-leaking prompts.
SKILL.md
1.0 KB, 194 tokens by cl100k_base, as published. Nobody here has run it
Secure Secrets for Agents
Handle agent credentials with env refs, redaction, least privilege, and non-leaking prompts.
When to Use
Use this Note when a Memoire or Studio run needs agent secret, env key, credential setup, redaction, api key handling.
Workflow
- Store secret references, not secret values, in Notes, prompts, configs, logs, and screenshots.
- Separate setup commands from verification commands so auth checks can run without exposing keys.
- Scope keys by provider, workspace, and purpose when the platform supports it.
- Redact command output before handing it to another agent or saving it in memory.
- Rotate or revoke credentials immediately if a secret appears in terminal, browser, screenshot, or artifact output.
Sources
What ships with it: 1 file
894 B alongside SKILL.md
- note.json894 B
Gives 0 of the 12 instructions most security skills give in 194 tokens
Counted across 648 of the 828 authors here whose files we hold, read 2026-08-07
- Parameterize all database queriesin 68 of 648, across 51 files
- Hash passwords using bcrypt, scrypt, or argon2in 49 of 648, across 36 files
- Apply rate limiting to authentication endpointsin 48 of 648, across 24 files
- Configure security headersin 35 of 648, across 19 files
- Validate all inputsin 32 of 648, across 24 files
- Validate all external input at the system boundaryin 29 of 648, across 19 files
- Run containers as a non-root userin 28 of 648, across 15 files
- Use httponly secure samesite cookies for sessionsin 26 of 648, across 15 files
- Run dependency audits before every releasein 21 of 648, across 10 files
- Encode output to prevent cross-site scriptingin 21 of 648, across 11 files
- Copy dependencies before source codein 20 of 648, across 9 files
- Store secrets in environment variablesin 20 of 648, across 18 files
Said here and by no other author read
- store secret references not values
- separate setup commands from verification commands
- scope keys by provider workspace and purpose
- redact command output before sharing or saving
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.