The Agent Skills Directory

[CREDENTIALS_UNSAFE]: The skill includes an auth login --chrome command designed to import active session cookies directly from the Chrome browser to facilitate authentication.
[DATA_EXFILTRATION]: The --deliver webhook:<url> flag provides a built-in mechanism to automatically POST command results, including private deck metadata and study statistics, to any external URL.
[EXTERNAL_DOWNLOADS]: The skill facilitates the installation of the ankiweb-pp-cli binary via npx -y @mvanhorn/printing-press-library and go install github.com/mvanhorn/printing-press-library/....
[COMMAND_EXECUTION]: The skill utilizes the ankiweb-pp-cli binary which has the capability to perform atomic file writes to the local system via the --deliver file:<path> argument.
[PROMPT_INJECTION]: The skill presents an attack surface for indirect prompt injection through the processing of community-provided deck data.
Ingestion points: Shared deck data, metadata, and reviews are ingested through the shared search and shared info commands in SKILL.md.
Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the processing instructions.
Capability inventory: The skill possesses the ability to exfiltrate data to webhooks, write to the local file system, and collect feedback as described in SKILL.md.
Sanitization: The instructions do not specify any validation or sanitization of the external content retrieved from the AnkiWeb shared catalog.

pp-ankiweb