indigoai-us/hq-core/hq-cowork-secrets
Claude Code and agent skill by indigoai-us/hq-core
- community
Checking that the SKILL.md file is still in the repository.
Run commands with HQ secrets from Cowork without exposing values.
Install
npx vskill@latest install indigoai-us/hq-core/hq-cowork-secretsSKILL.md
/hq-cowork-secrets — Use HQ secrets from a sandboxed agent
Runs commands with HQ secrets injected, and lists secret names, from inside Cowork — where the hq CLI and ~/.hq vault are unreachable. Routes through the host-side MCP server. The server never returns a secret value itself, and the secret-injecting tool refuses to run a shell or value-printing binary — but these tools run host commands with your privileges, so treat them as host-trusted, not an airtight boundary.
Args: $ARGUMENTS — list (+ optional company/prefix) or exec (keys + command). Infer from intent if not explicit.
Two modes
List names — mcp__hq__hq_secrets_list
Shows secret NAMES and path-based nested names. Values are never returned.
Omit company to use the active company; set personal: true for the caller's personal vault; prefix filters by path segment.
Run with secrets — mcp__hq__hq_secrets_exec
Injects named secrets as env vars of the same name into a child process and returns only the command's stdout/stderr.
cmd is argv (argv0 + args), NOT a shell string. The tool REFUSES to launch a shell or a raw value-printing binary as cmd[0] (sh/bash/zsh, printenv, env, echo, printf, cat, tee, node/python/perl/ruby, base64, xxd, strings, …) — this is defense-in-depth so an injected one-liner can't echo an injected secret back through the tool result. Invoke the actual consumer binary directly (e.g. vercel, aws, gh, or a deploy script). This is not airtight: a custom binary you control could still observe a secret it was given, so treat the tool as host-trusted.
Security rules (hard — from HQ core)
- No value-revealing path exists by design.
hq secrets get --revealis
NOT wrapped. Do not attempt to capture a value by echoing the env var.
- Cross-company isolation. Pass
companyexplicitly when crossing
contexts. If the scoped secret is missing or the command fails on auth, STOP and ask — never retry against a different company's vault.
- Never paste secrets inline. Always consume via
hq_secrets_exec
injection; never ask the user to paste a value into chat.
When to use this instead of /hq-secrets
Only inside Cowork or another sandboxed plugin host. On a host-side session, prefer the unprefixed /hq-secrets (or hq run / hq secrets exec).
Why this skill exists
hq secrets exec reads the encrypted vault under ~/.hq with the user's Cognito session — neither is visible from Cowork's Linux VM. The host-side MCP server runs the real command on the host and returns only the child's output. The server never returns a secret value itself, and refuses to run a shell / value-printing binary — but it runs host commands with your privileges, so it is host-trusted, not a cryptographic boundary.
Security
- Security scanPassed, 90 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingcore/packages/hq-pack-cowork/skills/hq-cowork-secrets/SKILL.md
Popularity
- Repository stars
- 89
- Repository forks
- 18
- 7-day trend score
- 0
Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/indigoai-us/hq-core/hq-cowork-secrets)