The Agent Skills Directory

[PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it is designed to process untrusted user content and local configuration files.
Ingestion points: The skill ingests text provided by the user for editing and reads marketing context from files such as .agents/product-marketing.md or .claude/product-marketing.md (SKILL.md).
Boundary markers: There are no explicit instructions or delimiters defined to isolate the context file contents or to prevent the agent from following instructions embedded within the edited text.
Capability inventory: Analysis of all files reveals no capabilities for network operations, file system modifications, or command execution; the skill is limited to providing text editing recommendations.
Sanitization: No sanitization or filtering logic is present for the ingested data.
[SAFE]: The skill does not perform any sensitive operations, handle credentials, or execute external code. All references are to local documentation and standard marketing practices.

copy-editing