The Agent Skills Directory

[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes untrusted content retrieved from external LinkedIn profiles.
Ingestion points: The skill ingests data from the apimaestro/linkedin-profile-posts Apify actor and user-pasted LinkedIn post text.
Boundary markers: There are no explicit markers or instructions to the model to ignore potential commands embedded within the analyzed posts.
Capability inventory: The skill has the capability to write JSON files to the local project directory and perform network requests via Apify, but it does not have access to sensitive system commands or credentials.
Sanitization: No sanitization or escaping of the ingested text is performed before it is processed by the model.
[EXTERNAL_DOWNLOADS]: The skill uses the Apify platform to download LinkedIn post history. This is documented as a core feature and requires user interaction to provide a username and authorize the cost.

post-scorer