The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill facilitates the installation of the printify-pp-cli tool via npx and go install from repositories associated with the project developer.
[REMOTE_CODE_EXECUTION]: The suggested installation workflows involve executing code retrieved from remote package registries and version control systems.
[COMMAND_EXECUTION]: The skill utilizes the Bash tool to run CLI commands for product automation, catalog browsing, and operational auditing.
[DATA_EXFILTRATION]: The CLI supports a --deliver webhook:<url> flag that allows command results (potentially containing sensitive shop or API data) to be transmitted to external URLs. Additionally, the feedback mechanism can send data to a remote endpoint if PRINTIFY_FEEDBACK_ENDPOINT is configured.
[PROMPT_INJECTION]: The skill ingests untrusted external data (CSV and JSON files) through multiple subcommands in SKILL.md. It lacks instructions for boundary markers or sanitization, making it vulnerable to indirect prompt injection. \n
Ingestion points: Data is read from files specified via flags like --product-file, --uploads-file, --manifest, --variants-file, --shipping-file, --csv, and --orders-file in SKILL.md. \n
Boundary markers: Absent. No delimiters or warnings are specified to prevent the agent from obeying instructions embedded in the processed files. \n
Capability inventory: Subprocess execution capability is present via the Bash tool as defined in the allowed-tools section of SKILL.md. \n
Sanitization: Absent. No sanitization or validation logic is defined for the content of ingested files.

pp-printify