Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion tools/skills_guard.py
Original file line number Diff line number Diff line change
Expand Up @@ -36,7 +36,7 @@
# Hardcoded trust configuration
# ---------------------------------------------------------------------------

TRUSTED_REPOS = {"openai/skills", "anthropics/skills"}
TRUSTED_REPOS = {"openai/skills", "anthropics/skills", "huggingface/skills"}

INSTALL_POLICY = {
# safe caution dangerous
Expand Down
1 change: 1 addition & 0 deletions tools/skills_hub.py
Original file line number Diff line number Diff line change
Expand Up @@ -329,6 +329,7 @@ class GitHubSource(SkillSource):
DEFAULT_TAPS = [
{"repo": "openai/skills", "path": "skills/"},
{"repo": "anthropics/skills", "path": "skills/"},
{"repo": "huggingface/skills", "path": "skills/"},
{"repo": "VoltAgent/awesome-agent-skills", "path": "skills/"},
{"repo": "garrytan/gstack", "path": ""},
{"repo": "MiniMax-AI/cli", "path": "skill/"},
Expand Down
2 changes: 1 addition & 1 deletion website/docs/developer-guide/creating-skills.md
Original file line number Diff line number Diff line change
Expand Up @@ -360,7 +360,7 @@ All hub-installed skills go through a security scanner that checks for:
Trust levels:
- `builtin` — ships with Hermes (always trusted)
- `official` — from `optional-skills/` in the repo (builtin trust, no third-party warning)
- `trusted` — from openai/skills, anthropics/skills
- `trusted` — from openai/skills, anthropics/skills, huggingface/skills
- `community` — non-dangerous findings can be overridden with `--force`; `dangerous` verdicts remain blocked

Hermes can now consume third-party skills from multiple external discovery models:
Expand Down
3 changes: 2 additions & 1 deletion website/docs/user-guide/features/skills.md
Original file line number Diff line number Diff line change
Expand Up @@ -351,6 +351,7 @@ Hermes can install directly from GitHub repositories and GitHub-based taps. This
Default taps (browsable without any setup):
- [openai/skills](https://github.com/openai/skills)
- [anthropics/skills](https://github.com/anthropics/skills)
- [huggingface/skills](https://github.com/huggingface/skills)
- [VoltAgent/awesome-agent-skills](https://github.com/VoltAgent/awesome-agent-skills)
- [garrytan/gstack](https://github.com/garrytan/gstack)

Expand Down Expand Up @@ -445,7 +446,7 @@ Important behavior:
|-------|--------|--------|
| `builtin` | Ships with Hermes | Always trusted |
| `official` | `optional-skills/` in the repo | Builtin trust, no third-party warning |
| `trusted` | Trusted registries/repos such as `openai/skills`, `anthropics/skills` | More permissive policy than community sources |
| `trusted` | Trusted registries/repos such as `openai/skills`, `anthropics/skills`, `huggingface/skills` | More permissive policy than community sources |
| `community` | Everything else (`skills.sh`, well-known endpoints, custom GitHub repos, most marketplaces) | Non-dangerous findings can be overridden with `--force`; `dangerous` verdicts stay blocked |

### Update lifecycle
Expand Down
Loading