The Agent Skills Directory

Indirect Prompt Injection (LOW): The skill provides an attack surface for indirect prompt injection as it processes untrusted data from user-provided files. 1. Ingestion points: The skill uses the Read tool to ingest content from a user-specified file path. 2. Boundary markers: Absent; there are no delimiters or instructions to treat the ingested content strictly as data or to ignore embedded commands. 3. Capability inventory: The skill utilizes Read and Write tools to perform its functions. 4. Sanitization: Absent; no validation, escaping, or filtering is performed on the content before it is processed by the AI agent.

ship-learn-next