The Agent Skills Directory

[SAFE]: The skill consists entirely of instructional markdown and reference files. It does not contain any executable scripts, shell commands, or external dependencies.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to process user-provided marketing copy. While this represents a potential surface for indirect prompt injection (where instructions hidden in the user's text could attempt to redirect the agent), the skill has no high-risk capabilities like network access or file-system writes that could be exploited.
Ingestion points: Processes user-supplied text during editing tasks as described in SKILL.md.
Boundary markers: None explicitly defined for user input in the instructions.
Capability inventory: No subprocess calls, network operations, or sensitive file access capabilities identified.
Sanitization: Not present, as the skill operates primarily as a text-to-text transformation tool.
[SAFE]: The instructions for reading .agents/product-marketing-context.md are standard for providing the agent with brand-specific context and do not target sensitive system or user configuration files.

copy-editing