The Agent Skills Directory

[PROMPT_INJECTION]: The skill processes untrusted external content (videos, blogs, whitepapers) without explicit boundary markers or instructions to ignore embedded commands. This creates a surface for indirect prompt injection where malicious instructions in the source material could influence the agent's behavior during the repurposing phase. Ingestion points: Processes YouTube videos, blog posts, and whitepapers provided by the user or fetched via external tools. Boundary markers: Absent. The instructions do not define delimiters for the external content or warn the agent to ignore instructions contained within it. Capability inventory: Mentions using bash for downloading content and scheduling tools to post to social platforms. Sanitization: Absent. No evidence of input validation or instruction filtering.

shadow-content-repurposer