Answer page · updated 2026-10-19
Is malicious-injection-quoted safe to install?
The Forge's scanner matched 1 medium-risk pattern in malicious-injection-quoted (aeonfun/aeon) (version 8884b68, scanned 2026-10-19): it has an instruction to ignore earlier instructions. A match is a reason to read those lines, not a verdict on the author.
github.com/
The facts
- Repository
- aeonfun/aeon
- File
- scripts/tests/skill-scan-fixtures/malicious-injection-quoted/SKILL.md
- Size
- 214 bytes
- Versions scanned
- 1 (newest 8884b68)
- 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)
- Low-severity notes
- 1
- Field reports
- none yet
Same repository
110 other skills from aeonfun/aeon have a public scan here: 6 with a high-risk pattern, 15 with a medium-risk pattern, 89 with no matches.
- scripts/tests/skill-scan-fixtures/malicious-exfil-query no matches
- scripts/tests/skill-scan-fixtures/malicious-injection medium-risk pattern
- scripts/tests/skill-scan-fixtures/malicious-injection-keyword medium-risk pattern
- scripts/tests/skill-scan-fixtures/malicious-rce-procsub no matches
- scripts/tests/skill-scan-fixtures/malicious-rce-source high-risk pattern
- scripts/tests/skill-scan-fixtures/malicious-rmrf high-risk pattern
Skill scan
| Pattern | Severity | Line | Source |
|---|---|---|---|
| An instruction to ignore earlier instructions FS-INJ-001 | medium | 5 | line 5 on GitHub |
| An instruction to ignore earlier instructions FS-INJ-001 | low | 4 | line 4 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/aeonfun/aeon/8884b68d0da62c071851efc7e09e9b00169a65c6/scripts/tests/skill-scan-fixtures/malicious-injection-quoted/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.