Answer page · updated 2026-10-19
Is audit-llm-security safe to install?
The Forge's scanner matched 1 medium-risk pattern in audit-llm-security (kensaurus/skills) (version 95c89e5, 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
- kensaurus/skills
- File
- skills/audit-llm-security/SKILL.md
- Size
- 6.7 KB
- Versions scanned
- 1 (newest 95c89e5)
- 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
172 other skills from kensaurus/skills have a public scan here: 0 with a high-risk pattern, 1 with a medium-risk pattern, 171 with no matches.
- skills/audit-i18n no matches
- skills/audit-infra-cost no matches
- skills/audit-langfuse-llm no matches
- skills/audit-monetization-iap no matches
- skills/audit-payment-system no matches
- skills/audit-performance no matches
Skill scan
| Pattern | Severity | Line | Source |
|---|---|---|---|
| An instruction to ignore earlier instructions FS-INJ-001 | medium | 109 | line 109 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/kensaurus/skills/95c89e5da4376fd6e31b0a3156011275620f9f91/skills/audit-llm-security/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.