Answer page · updated 2026-10-19
Is setup-matt-pocock-skills safe to install?
The Forge's scanner matched 2 medium-risk patterns in setup-matt-pocock-skills (VoDaiLocz/kilo-kit-mcp) (version 0448e6c, scanned 2026-10-19): it changes the agent's standing files or memory. A match is a reason to read those lines, not a verdict on the author.
github.com/
The facts
- Repository
- VoDaiLocz/kilo-kit-mcp
- File
- skills/engineering/setup-matt-pocock-skills/SKILL.md
- Size
- 6.7 KB
- Versions scanned
- 1 (newest 0448e6c)
- 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
- 2
- Field reports
- none yet
Same repository
163 other skills from VoDaiLocz/kilo-kit-mcp have a public scan here: 3 with a high-risk pattern, 1 with a medium-risk pattern, 159 with no matches.
- skills/engineering/repomix no matches
- skills/engineering/research no matches
- skills/engineering/resolving-merge-conflicts no matches
- skills/engineering/shopify no matches
- skills/engineering/structured-outputs no matches
- skills/engineering/tdd no matches
Skill scan
| Pattern | Severity | Line | Source |
|---|---|---|---|
| Changes the agent's standing files or memory FS-PER-001 | medium | 83 | line 83 on GitHub |
| Changes the agent's standing files or memory FS-PER-001 | medium | 84 | line 84 on GitHub |
| Changes the agent's standing files or memory FS-PER-001 | low | 74 | line 74 on GitHub |
| Changes the agent's standing files or memory FS-PER-001 | low | 87 | line 87 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/VoDaiLocz/kilo-kit-mcp/0448e6c050b84e0c0be0030593bd51cabbce3c81/skills/engineering/setup-matt-pocock-skills/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.