Answer page · updated 2026-10-19
Is hunting-for-suspicious-scheduled-tasks safe to install?
The Forge's scanner matched 1 medium-risk pattern in hunting-for-suspicious-scheduled-tasks (mukul975/Anthropic-Cybersecurity-Skills) (version 54a7988, scanned 2026-10-19): it installs a scheduled task or shell start-up hook. A match is a reason to read those lines, not a verdict on the author.
github.com/
The facts
- Repository
- mukul975/Anthropic-Cybersecurity-Skills
- File
- skills/hunting-for-suspicious-scheduled-tasks/SKILL.md
- Size
- 4.8 KB
- Versions scanned
- 1 (newest 54a7988)
- 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
817 other skills from mukul975/Anthropic-Cybersecurity-Skills have a public scan here: 41 with a high-risk pattern, 40 with a medium-risk pattern, 736 with no matches.
- skills/hunting-for-spearphishing-indicators no matches
- skills/hunting-for-startup-folder-persistence no matches
- skills/hunting-for-supply-chain-compromise no matches
- skills/hunting-for-t1098-account-manipulation no matches
- skills/hunting-for-unusual-network-connections no matches
- skills/hunting-for-unusual-service-installations no matches
Skill scan
| Pattern | Severity | Line | Source |
|---|---|---|---|
| Installs a scheduled task or shell start-up hook FS-PER-002 | medium | 92 | line 92 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/mukul975/Anthropic-Cybersecurity-Skills/54a798831d2266a3ca61ce68a7acb80b81160d57/skills/hunting-for-suspicious-scheduled-tasks/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.