The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill presents a surface for indirect prompt injection because it ingests untrusted external data and possesses the capability to publish content to the user's LinkedIn account.
Ingestion points: The skill takes source material in various formats, such as tweets, threads, YouTube transcripts, and blog posts, which can be provided directly or via links (SKILL.md, Step 1).
Boundary markers: There are no explicit delimiters or instructions provided to the agent to ignore or isolate potential commands embedded within the source content.
Capability inventory: The agent utilizes the lib.publish tool to post content to LinkedIn upon approval (SKILL.md, Step 9).
Sanitization: The instructions do not specify any validation, filtering, or sanitization of the ingested source material before it is processed and published.

linkedin-repurposer