onlyterp/hermes-optimization-guide/hermes-security-review
Claude Code and agent skill by onlyterp/hermes-optimization-guide
- community
Checking that the SKILL.md file is still in the repository.
Review Hermes settings for security risks.
Install
npx vskill@latest install onlyterp/hermes-optimization-guide/hermes-security-reviewSKILL.md
Hermes Security Review
Check the settings that decide who can drive this agent, what it may run, and what it can leak. Then report risks by severity, each with a concrete fix.
When to Use
- Before exposing Hermes on a messaging platform, to other people, or on a server.
- After adding MCP servers, plugins, or skills from outside sources.
- As a monthly cron job.
Procedure
Run commands with the terminal tool. Never print secret values. Read key names only. Change nothing without the user's approval.
- Approval and safety settings:
``bash hermes config get approvals.mode hermes config get approvals.cron_mode hermes config get approvals.unattended_mode hermes config get security.redact_secrets hermes config get security.protected_instruction_files hermes config get security.protected_instruction_extra_patterns hermes config get memory.write_approval hermes config get skills.write_approval hermes config get security.allow_private_urls hermes config get gateway.allow_all_users hermes config get terminal.backend hermes config get auth.adopt_external_logins ``
- Secrets file permissions. Expect
600:
``bash ENV_FILE="$(hermes config env-path)" stat -c '%a' "$ENV_FILE" 2>/dev/null || stat -f '%Lp' "$ENV_FILE" ``
- Who can talk to it. List allowlist-related key names in the secrets file, without values, plus pending pairings:
``bash grep -oE '^[A-Z_]*(ALLOWED_USERS|ALLOWED_CHATS|ALLOW_ALL_USERS)=' "$(hermes config env-path)" hermes pairing list hermes gateway status ``
For each platform the gateway runs, confirm that an allowlist or DM pairing is in place.
- Supply chain:
``bash hermes security audit # OSV.dev scan of the venv, plugin deps, pinned MCP servers hermes skills audit # re-scan hub-installed skills hermes plugins list --user hermes mcp list ``
- Rate what you found:
| Severity | Condition | |
|---|---|---|
| Critical | gateway.allow_all_users: true or any *_ALLOW_ALL_USERS=true on a profile with terminal access. approvals.mode: off on a profile reachable from messaging. | |
| High | Secrets file readable by other users (not 600). A platform running with no allowlist and no pairing. security.redact_secrets: false. Known vulnerabilities from hermes security audit. | |
| Medium | approvals.cron_mode or approvals.unattended_mode not deny. security.protected_instruction_files: false. MCP servers from unknown publishers with broad tool access and no include filter. | |
| Low | security.allow_private_urls: true on a machine with sensitive internal services. auth.adopt_external_logins: true where Codex CLI or Claude Code logins should stay separate. security.protected_instruction_extra_patterns missing .hermes.md, agents.override.md or *.mdc on a profile that works in repos other people wrote. memory.write_approval or skills.write_approval off on a profile other people can message. |
- Report findings by severity with the exact fix for each:
hermes config set …,chmod 600 …, an allowlist line, orhermes pairing revoke …. Ask which to apply.
Verification
- After fixes, re-run steps 1–3. Critical and High findings should be gone.
hermes security auditreports no known-vulnerable packages, or only ones the user accepted.
Pitfalls
- Container terminal backends (for example Docker) skip dangerous-command approval checks by design, because the container is the boundary. That is only safe if the container really is locked down.
- The protected-file gate covers project files only. The Hermes home is exempt, so the agent can rewrite
~/.hermes/SOUL.mdwithout a prompt, and memory and skills are gated only by their ownwrite_approvalsettings. - Never paste the contents of
.env,auth.json, or any key into the chat or a report. hermes security auditqueries OSV.dev over the network. Tell the user before running it on an air-gapped host.
Security
- Security scanPassed, 100 of 100Pattern checks on the skill's files.
- Model reviewNot runA model review is scheduled for the next rescan.
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskills/hermes-security-review/SKILL.md
Popularity
- Repository stars
- 705
- Repository forks
- 58
- 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/onlyterp/hermes-optimization-guide/hermes-security-review)