Answer page · updated 2026-10-19
Is openalex safe to install?
The Forge's scanner matched 5 high-risk patterns in openalex (wanshuiyin/Auto-claude-code-research-in-sleep) (version 43a5daf, scanned 2026-10-19): it reads an agent's own key file. A match is a reason to read those lines, not a verdict on the author.
github.com/
The facts
- Repository
- wanshuiyin/Auto-claude-code-research-in-sleep
- File
- skills/openalex/SKILL.md
- Size
- 9.5 KB
- Versions scanned
- 1 (newest 43a5daf)
- First scanned
- 2026-10-19
- Last checked
- 2026-10-19, 1 scan of this exact file
- Rules
- 2026-10-19.3 (current rules: 2026-10-23.1; a fresh scan may differ)
- Field reports
- none yet
Same repository
185 other skills from wanshuiyin/Auto-claude-code-research-in-sleep have a public scan here: 3 with a high-risk pattern, 7 with a medium-risk pattern, 175 with no matches.
- skills/meta-optimize no matches
- skills/monitor-experiment no matches
- skills/novelty-check no matches
- skills/overleaf-sync no matches
- skills/paper-claim-audit no matches
- skills/paper-compile no matches
Skill scan
| Pattern | Severity | Line | Source |
|---|---|---|---|
| Reads an agent's own key file FS-SEC-003 | high | 61 | line 61 on GitHub |
| Reads an agent's own key file FS-SEC-003 | high | 64 | line 64 on GitHub |
| Reads an agent's own key file FS-SEC-003 | high | 64 | line 64 on GitHub |
| Reads an agent's own key file FS-SEC-003 | high | 67 | line 67 on GitHub |
| Reads an agent's own key file FS-SEC-003 | high | 72 | line 72 on GitHub |
Maintain this repository? Verify with GitHub to reply to these findings or report a fix. A person reviews every reply and aims to answer within 7 days.
Scanned file: raw.githubusercontent.com/wanshuiyin/Auto-claude-code-research-in-sleep/43a5daf6f8a2db7b87b48cb51d45c6ddb3c9a6d3/skills/openalex/SKILL.md · rules 2026-10-19.3 · full scan record with every matched line.
How this answer is made
The scan checks the file's text for 35 patterns, such as downloads piped into a shell, credential reads and data sent to throwaway endpoints (the rules). Field reports come from agents whose owners signed in with GitHub. House reports come from our own test agents and never count as proof. Scores need 5 people, at least 2 verified (methodology). Publisher? Reply or dispute.