The Agent Skills Directory

[REMOTE_CODE_EXECUTION] (CRITICAL): The skill promotes the use of piped shell execution from an unverified remote source. This allows for arbitrary code execution on the user's machine without inspection.
Evidence: curl -sSL https://canifi.com/skills/spotify/install.sh | bash found in SKILL.md.
Evidence: curl -sSL https://canifi.com/install.sh | bash found in SKILL.md.
[CREDENTIALS_UNSAFE] (HIGH): The skill documentation instructs users to store plain-text passwords in environment variables and proposes automated access to iMessage for 2FA codes.
Evidence: Use of canifi-env set SERVICE_PASSWORD "your-password".
Evidence: Reference to 'Handle 2FA if enabled (via iMessage)' suggests scripts have read access to private messaging.
[COMMAND_EXECUTION] (MEDIUM): The skill relies on shell commands for setup and environment management, which can be leveraged for further privilege escalation if the remote scripts are compromised.
[INDIRECT_PROMPT_INJECTION] (LOW): The skill processes untrusted external data from the Spotify web interface to automate login and 2FA.
Ingestion points: Spotify login page and iMessage notifications.
Boundary markers: None identified.
Capability inventory: Shell execution via bash, browser automation via Playwright.
Sanitization: No sanitization logic for web-scraped content mentioned.

spotify