The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process user-supplied data regarding product context, research, and constraints to generate pricing advice. While this represents a potential surface for indirect prompt injection, the risk is negligible as the skill lacks executable capabilities.
Ingestion points: The skill explicitly requests "Context about your product, feature, or problem" and "Relevant data, research, or constraints" within the SKILL.md file.
Boundary markers: No specific delimiters or safety instructions are defined to separate user-provided data from the agent's internal logic.
Capability inventory: The skill does not possess any capabilities for file writing, command execution, or network operations.
Sanitization: No input validation or sanitization mechanisms are implemented for the ingested data.
[SAFE]: The analyzed content is purely informational and serves as a documentation-based skill to guide the agent's reasoning. It does not include any scripts, dependencies, or hidden commands.

monetizing-innovation