The Agent Skills Directory

[SAFE]: The skill operates entirely within the scope of its stated purpose, generating text-based pricing strategies from user inputs.
[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data through inputs like product_description and competitor_prices (SKILL.md). These inputs are processed by the model to generate copy recommendations. While the skill lacks explicit boundary markers or "ignore instructions" warnings for these inputs, it does not have access to sensitive tools or file system operations that would allow for a malicious payload to result in data exfiltration or system compromise. The impact is limited to the generation of potentially biased or incorrect pricing copy.
[EXTERNAL_DOWNLOADS]: The skill references a local file rmbc-context/SKILL.md to load framework definitions. This is a standard practice for modular skills and does not involve remote network calls or unverifiable third-party dependencies.

pricing-strategy