The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill's core functionality involves processing untrusted user input (topics, keywords, target audience) and incorporating it into markdown files, which represents a potential surface for indirect prompt injection.
Ingestion points: External data enters the agent context through user-specified topics and keywords during the initialization step in SKILL.md.
Boundary markers: The instructions do not employ explicit delimiters or specialized directives to prevent the agent from following instructions that might be embedded within user-supplied content.
Capability inventory: The skill leverages the agent's file-writing capabilities to generate .md blog posts, as defined in the 'Output Format' section of SKILL.md.
Sanitization: There are no provisions for filtering, escaping, or validating the content provided by the user before it is processed or written to disk.

blogger-pro