Skill scan · first seen 2026-10-19 · scanned 1 time
openalex · wanshuiyin/Auto-claude-code-research-in-sleep
Skill scan · rules 2026-10-19.3
High-risk pattern
Flagged: 5 high-risk patterns found. Don't install it until a person has read the flagged lines.
| Severity | Pattern | Line | What it says |
|---|---|---|---|
| High | Reads an agent's own key file FS-SEC-003 An agent's .env or credentials file holds every API key it has (the most common skill theft target). | 61 | .claude/.env |
| High | Reads an agent's own key file FS-SEC-003 An agent's .env or credentials file holds every API key it has (the most common skill theft target). | 64 | .claude/.env |
| High | Reads an agent's own key file FS-SEC-003 An agent's .env or credentials file holds every API key it has (the most common skill theft target). | 64 | .claude/.env |
| High | Reads an agent's own key file FS-SEC-003 An agent's .env or credentials file holds every API key it has (the most common skill theft target). | 67 | .claude/.env |
| High | Reads an agent's own key file FS-SEC-003 An agent's .env or credentials file holds every API key it has (the most common skill theft target). | 72 | .claude/.env |
Fingerprint4c853b646987…
sha256:4c853b646987c4472a8360e044ad232aa9731dcfb60c7183073e8e5f3e6ac9c1
"Flagged" here means the scanner matched a high-risk text pattern; it is not a Watchlist flag, which needs three verified people.
Maintainer response
- Result at the scanned commit 43a5daf6f8a2: flagged, a high-risk pattern matched (the lines above).
- Maintainer response (29 Oct 2026): fixed in #482 (commit a3a847b, 29 Oct 2026). The thread. The .claude/.env setup was replaced with exporting OPENALEX_API_KEY and OPENALEX_EMAIL in the shell before starting Claude Code. The fix landed on 29 Oct, the day after our notice.
- Rescan at the current commit a3a847b421c6 (29 Oct 2026, rules 2026-10-23.1): clear, no known pattern matched.
A match was a reason to read the line, not a verdict on the author, and we found no sign of malice. A clear rescan means no known pattern matched, not proof the file is safe.
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.
Share
This skill reads an agent's own key file: a high-risk pattern, not proof of malice. Read the line before your agent installs it: https://theagentforge.io/scan/4c853b646987c4472a8360e044ad232aa9731dcfb60c7183073e8e5f3e6ac9c1?from=shareThis page shows text patterns in one exact version of the file (fingerprint above), not a judgement of its author. Publisher? Reply or dispute, and we add your reply here.
Check your own skills
Or paste this into your agent once. It then checks every skill before installing it:
Read https://theagentforge.io/skill.md and use it: before you install any skill, plugin or MCP server, check it with the Forge.Free, no account. Read the skill file first.