afrexai-openclaw-mastery

clawhub:afrexai-openclaw-mastery

View source
B
84/100

First Seen

Feb 19, 2026

Last Scanned

Feb 22, 2026

Findings

3

Score

84/100

MEDIUM 2
LOW 1

Findings (3)

MEDIUM
Autonomous agent spawning
L345

Detects autonomous sub-agent or cron-based execution without human oversight

isolated session + autonomous
FIX

Remove directives that force the agent to call specific tools or APIs not required for the skill's stated functionality. Tool calls should be determined by user intent, not embedded directives.

FP?

Likely FP if the skill legitimately needs to call other tools as part of its workflow (e.g., a deployment skill that calls git and cloud CLI tools).

MEDIUM
Unattended auto-update
L524

Detects automatic package or skill updates via cron or scheduled tasks without verification

update --all
FIX

Avoid installing packages from private or unofficial registries specified in skill instructions. Verify the registry URL is legitimate and use scoped packages with registry configuration.

FP?

Likely FP if the private registry is a well-known enterprise registry (e.g., GitHub Packages, Artifactory) documented in the project setup.

LOW
Global package installation
L50

Detects global installation of packages which affects the host system

npm install -g o
FIX

Replace npm install -g with a local install (npm install --save-dev) or use npx with a pinned version. Global installs modify the system and risk supply chain attacks.

FP?

Likely FP if the global install is for a well-known CLI tool (e.g., typescript, eslint) in setup documentation, though the supply chain risk remains real.