The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process potentially untrusted external data, which creates a surface for indirect prompt injection.
Ingestion points: The skill processes user-supplied information including product descriptions, market context, customer insights, and business data via the $ARGUMENTS placeholder in SKILL.md.
Boundary markers: The instructions do not define clear delimiters or specific instructions for the agent to ignore potentially malicious content embedded within the input data.
Capability inventory: The skill is limited to generating text-based strategy canvases and does not utilize any tools or scripts for network operations, file system modification, or command execution.
Sanitization: There is no evidence of input validation, filtering, or sanitization to handle instructions embedded in the user data.
[SAFE]: The skill provides links to external resources for documentation and templates.
It references a product strategy template hosted on Google Docs, a well-known productivity service.
It provides several links to a product management publication for further educational reading.

product-strategy