The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read local context files to inform its offer design recommendations, creating a potential surface for indirect prompt injection if those files contain malicious instructions.
Ingestion points: SKILL.md directs the agent to check for and read .agents/product-marketing.md, .claude/product-marketing.md, or product-marketing-context.md before proceeding.
Boundary markers: The skill lacks explicit delimiters or instructions for the agent to ignore natural language commands found within these ingested context files.
Capability inventory: The skill contains no executable scripts, tool definitions, subprocess calls, network operations, or file-writing capabilities. Its output is limited to a structured Markdown "Offer Brief."
Sanitization: No sanitization or filtering is performed on the data read from the context files.
[EXTERNAL_DOWNLOADS]: The skill card and documentation reference external URLs for installation and support.
Evidence: Links to github.com/JasonColapietro and skills.suedeai.ai are provided in CARD.md and reference files.
Context: These resources belong to the verified author (jasoncolapietro) and are standard for skill documentation and updates.

suede-offers