The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted source content to generate social media variants, creating a potential surface for indirect prompt injection attacks where the input might contain hidden instructions.
Ingestion points: The source_content field defined in the Input Schema of SKILL.md.
Boundary markers: Absent; the workflow does not include instructions or delimiters to isolate the source content from the agent's core processing logic.
Capability inventory: The skill is restricted to text generation and analysis; it does not utilize tools for network access, file system modification, or command execution.
Sanitization: Absent; there are no specified steps to filter or escape the input content before it is interpolated into the workflow.

content-repurposer