The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied data which represents a potential surface for indirect prompt injection attacks.
Ingestion points: Untrusted data enters the context via the Title, Primary Keyword, Intent, Niche / Industry, Brand, Target Audience, and Key Themes / Context fields.
Boundary markers: The prompt template uses curly braces (e.g., {Insert Title}) to delineate user input, but it lacks specific instructions for the agent to ignore any malicious commands embedded within that data.
Capability inventory: The skill has no capabilities to execute shell commands, perform network requests, or write to the file system.
Sanitization: There is no evidence of input sanitization or validation logic to filter potentially malicious text provided by users.
[SAFE]: The skill is entirely text-based and does not attempt to access sensitive files, environment variables, or hardcoded credentials. It does not use the !command syntax or any other dynamic context injection methods.

wordpress-centric-high-seo-optimized-blogwriting-skill