voyageai-skill

clawhub:voyageai-skill

View source
B
85/100

First Seen

Feb 18, 2026

Last Scanned

Feb 22, 2026

Findings

3

Score

85/100

HIGH 1
LOW 2

Findings (3)

HIGH
Destructive actions with code execution
L107

Skill has destructive capabilities AND can execute arbitrary code. This combination enables ransomware-like attacks.

[destructive] delete --db mydb --collection + [executes_code] eval (
FIX

Isolate security-sensitive operations from untrusted data flows. Use separate execution contexts or privilege levels for operations that handle both user input and sensitive resources.

FP?

Likely FP if the toxic flow analysis connected two unrelated code paths, or if the data undergoes transformation that removes the taint (e.g., parsed as a known enum value).

LOW
Global package installation
L48

Detects global installation of packages which affects the host system

npm install -g v
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.

LOW
Shell profile modification for persistence
L189

Detects instructions to modify shell config files for environment persistence

>> ~/.bashrc && source ~/.bashrc
FIX

Avoid modifying shell profiles (.bashrc, .zshrc, .profile) programmatically. Instruct users to add PATH entries manually, or use a version manager (nvm, pyenv) instead.

FP?

Likely FP if the match is documentation showing how to add a tool to PATH manually, especially if it only appends to PATH without modifying other settings.