The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from user input and external URLs via the WebFetch tool. This creates a surface for indirect prompt injection where instructions embedded in the source material could influence the agent's behavior during content adaptation.\n- Ingestion points: SKILL.md identifies source content sources as direct text, URLs, and video/audio transcripts.\n- Boundary markers: The prompt instructions do not provide delimiters or warnings to the agent regarding potential instructions inside the source content.\n- Capability inventory: The skill is primarily focused on text rewriting and analysis; it does not possess capabilities for file writing or unauthorized network access.\n- Sanitization: The instructions do not specify any sanitization or validation of the ingested external content.\n- [EXTERNAL_DOWNLOADS]: The skill utilizes a WebFetch capability to retrieve content from external URLs for analysis. This is documented as a standard feature of the skill to support content repurposing.

skill-content-repurposing