The Agent Skills Directory

[SAFE]: The skill consists exclusively of markdown instructions, templates, and frameworks for transforming content (e.g., articles to social media posts).
[NO_CODE]: There are no executable scripts, shell commands, or external code dependencies provided with this skill.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external content such as articles and video transcripts.
Ingestion points: External text sources provided by the user (articles, video/podcast transcripts) as mentioned in the transformation instructions.
Boundary markers: None explicitly defined in the prompts to separate user data from instructions.
Capability inventory: The skill only performs text generation; it lacks file-system access, network operations, or code execution capabilities.
Sanitization: No sanitization or filtering is applied to the input data.
Conclusion: Given the lack of dangerous capabilities, the risk of indirect prompt injection is negligible and restricted to the accuracy of the text transformation.

content-repurpose