The Agent Skills Directory

[SAFE]: The skill operates as a knowledge base and prompt generator for sales enablement tasks. Analysis of the instructions and reference files shows no malicious code, unauthorized network access, or persistence mechanisms.
[INDIRECT_PROMPT_INJECTION]: The skill attempts to read project-marketing context from files such as .agents/product-marketing.md. 1. Ingestion points: Reads .agents/product-marketing.md, .claude/product-marketing.md, or product-marketing-context.md (specified in SKILL.md). 2. Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded commands within these context files. 3. Capability inventory: The skill is limited to text generation and does not have access to tools for file writing, network requests, or shell execution. 4. Sanitization: There is no explicit sanitization or validation of the content read from the project files. 5. Risk: Since the skill only generates text and has no high-privilege capabilities, the risk of indirect prompt injection is minimal.

sales-enablement