The Agent Skills Directory

[SAFE]: The skill consists entirely of markdown instructions and evaluation data. No executable scripts, network requests, or dangerous commands were found within the provided files.
[INDIRECT_PROMPT_INJECTION]: The skill contains instructions to ingest data from product marketing context files (e.g., .agents/product-marketing.md). While this presents a potential ingestion surface, the skill has no dangerous capabilities to exploit.
Ingestion points: SKILL.md references reading .agents/product-marketing.md, .claude/product-marketing.md, and product-marketing-context.md.
Boundary markers: Absent; the skill does not provide specific delimiters or warnings for the ingested content.
Capability inventory: No subprocess calls, network operations, or file-write capabilities are present in the skill.
Sanitization: Absent; the skill relies on standard agent processing without custom sanitization logic.

paywalls