scope-drift-detection-device
scope-drift-detection-device is a Blue team & detection skill for AI agents, published by SCStelz in the security-investigator repository on GitHub. Skillspace rates scope-drift-detection-device F (45/100) and the safety scan rated it risky; the rating is based on static analysis only.
Risky. This skill has patterns associated with unsafe behaviour. Read the source carefully before running it.
Use this skill when asked to detect scope drift, behavioral expansion, or process baseline deviation on devices or endpoints. Triggers on keywords like "device drift", "device process drift", "endpoint drift", "process baseline", "device behavioral change", or when investigating whether a device has gradually expanded its process execution beyond an established baseline. This skill builds a configurable-window behavioral baseline using DeviceProcessEvents, compares baseline with recent activity, computes a weighted Drift Score across 5 dimensions (Volume, Processes, Accounts, Process Chains, Signing Companies), and correlates with SecurityAlert, DeviceInfo (for uptime corroboration via MDE sensor health), and command-line pattern analysis. Supports fleet-wide and single-device modes.
- Grade
- F
- Quality
- 45 / 100
- Safety
- Risky
- GitHub stars
- 230
Unproven: rated by static analysis only, not yet compared head-to-head.
This rating describes the version of the repository we crawled; it may have changed since.
Our review
- Architecture
- 62 / 100
- Maturity
- Basic: a single SKILL.md
- Security scan
- High-risk patterns
- License
- MIT
- Adoption
- Adopted by 0 other repositories, in 0 collections
What the scanner flagged
- exfiltration language
Not checked yet
- Not judged on the rubric yet (not a contender in its category)
- No blind task eval yet
- Scope (portable / vendor / repo-internal) not assessed; only the top of each category is read for scope
- Sibling files (scripts, references) not fetched; security scan covers SKILL.md only
Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.