The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its core function of processing external data into structured documents. • Ingestion points: The skill explicitly instructs the agent to gather 'metrics, stories, photography, goals, progress data' from the user as part of the 'Content Generation Workflow' in SKILL.md. • Boundary markers: The instructions lack explicit boundary markers or warnings for the agent to ignore potentially malicious instructions embedded within the user-provided metrics or stories. • Capability inventory: The skill grants the agent the capability to generate and save documents in PDF, DOCX, and PPTX formats, as listed in the 'Supported Outputs' section of SKILL.md. • Sanitization: There is no mention of sanitizing, escaping, or validating the user-provided content before it is processed and formatted into the final report artifacts.

photo-magazine