Skip to content
Back to skills

Block Secret Store Reads

BSecurity

Best-effort guard against an agent reading credentials from the shell: cat, grep, sed, cp, tar, base64, source or < on ~/.ssh (not .pub), ~/.aws, ~/.npmrc, ~/.netrc, ~/.kube, ~/.gnupg, agent CLI dirs, browser login DBs, wallets, .env (not .env.example), *.tfstate; interpreter one-liners naming them; gh auth token, aws sts get-session-token, git credential fill. Asks on env/printenv dumps. Misses: scripts, unresolved variables, xargs lists, $(...) results.

  • 3 stars
  • 0 votes
  • 0 copies
  • 0 views
  • Added October 3, 2026
ai-agentsshellawsgit

Works with

  • cli

Security analysis

B88/100
  • criticalSends environment variables or credentials to an external URL

Pro shows the line behind each finding and how to fix it

Scanned October 3, 2026

npx -y skills add open-coder-ai/chock-catalog --skill block-secret-store-reads --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Block Secret Store Reads?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Block Secret Store Reads
[![Security: B — Skills Directory](https://www.skillsdirectory.com/api/skills/open-coder-ai-block-secret-store-reads/badge)](https://www.skillsdirectory.com/skills/open-coder-ai-block-secret-store-reads)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: block-secret-store-reads
description: "Best-effort guard against an agent reading credentials from the shell: cat, grep, sed, cp, tar, base64, source or < on ~/.ssh (not .pub), ~/.aws, ~/.npmrc, ~/.netrc, ~/.kube, ~/.gnupg, agent CLI dirs, browser login DBs, wallets, .env (not .env.example), *.tfstate; interpreter one-liners naming them; gh auth token, aws sts get-session-token, git credential fill. Asks on env/printenv dumps. Misses: scripts, unresolved variables, xargs lists, $(...) results."
metadata:
  chock.artifact: rule
  chock.enforcement: advise
  chock.coverage_without_chock: advisory
---

# Block Secret Store Reads

Best-effort guard against an agent reading credentials from the shell: cat, grep, sed, cp, tar, base64, source or < on ~/.ssh (not .pub), ~/.aws, ~/.npmrc, ~/.netrc, ~/.kube, ~/.gnupg, agent CLI dirs, browser login DBs, wallets, .env (not .env.example), *.tfstate; interpreter one-liners naming them; gh auth token, aws sts get-session-token, git credential fill. Asks on env/printenv dumps. Misses: scripts, unresolved variables, xargs lists, $(...) results.

```
never(read|print): credential_stores(~/.ssh(not_*.pub)|~/.aws|~/.npmrc|~/.netrc|~/.kube|~/.gnupg|agent_cli_dirs|browser_dbs|wallets|.env(not_.env.example)|*.tfstate)|tokens(gh_auth_token|aws_sts|git_credential_fill), via(cat|grep|sed|cp|tar|base64|source|<|interpreter)
ask: env|printenv|set|export_-p  # dumps every secret; if(value_needed): ask_person_for_that_value
```

This skill is advisory: the client reading it has no mechanism to enforce it. The same policy compiled by `chock` can refuse an agent's shell command before it runs. See https://github.com/open-coder-ai/chock

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…