pp-squarespace

Warn

Audited by Gen Agent Trust Hub on Jul 27, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDATA_EXFILTRATIONCREDENTIALS_UNSAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill facilitates the installation of the squarespace-pp-cli tool using npx from @mvanhorn/printing-press-library or go install from github.com/mvanhorn/printing-press-library. These resources are owned by the author's organization but reside on external platforms.
  • [COMMAND_EXECUTION]: The skill uses the Bash tool to execute installation scripts and various commerce management commands through the CLI.
  • [DATA_EXFILTRATION]: The CLI tool features a --deliver webhook:<url> parameter which allows the output of any command—potentially containing customer contacts, order details, or billing information—to be sent to an arbitrary external URL. Furthermore, the feedback command can be configured to upload local data to a remote endpoint via the SQUARESPACE_FEEDBACK_ENDPOINT variable.
  • [CREDENTIALS_UNSAFE]: The skill interacts with sensitive authentication data, specifically a session cookie file located at ~/.config/squarespace/account-cookie.txt and the COMMERCE_AUTHORIZATION environment variable. The handling of these credentials by the agent increases the risk of session hijacking or token exposure.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) because it retrieves and processes untrusted content from Squarespace APIs (e.g., via get-orders, contacts get, and get-profiles). This data enters the agent context without specified boundary markers or sanitization logic. Given the skill's high-privilege capabilities, such as network exfiltration via webhooks and file system access, an injection could lead to unauthorized data access or exfiltration.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Jul 27, 2026, 10:21 AM
Security Audit — agent-trust-hub — pp-squarespace