First Seen
Feb 18, 2026
Last Scanned
Feb 22, 2026
Findings
4
Score
85/100
Findings (4)
Skill has destructive capabilities AND can execute arbitrary code. This combination enables ransomware-like attacks.
[destructive] rm -rf / + [executes_code] exec(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.
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).
Detects global installation of packages which affects the host system
npm install -g @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.
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.
Detects eval() or exec() used for dynamic code execution
exec(
cReplace eval()/exec() with a safer alternative such as json.loads(), ast.literal_eval(), or a purpose-built parser.
Likely FP if the matched text contains 'exec' as part of a word (e.g., 'execute', 'execution') rather than an actual eval() or exec() call.
Detects Docker or docker-compose commands passing credentials via environment variables
docker run --rm -t -e ANTHROPIC_AUTH_TOKEN=Remove credential values from Docker environment flags (-e) and docker-compose environment sections. Use Docker secrets, .env files (in .dockerignore), or a secrets manager.
Likely FP if the Docker environment variable has an empty or placeholder value (e.g., -e API_KEY= or -e PASSWORD=changeme) in setup documentation.