The Agent Skills Directory

[PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection due to its core functionality of fetching and processing external data.
Ingestion points: The skill uses scrapegraph /v1/smartscraper and linkup /fetch to ingest content from arbitrary external URLs provided in the website_url and url parameters.
Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the prompt templates shown.
Capability inventory: The skill possesses the capability to perform network operations (orth api run) and process the resulting data through LLM-powered scrapers, creating a path for data from external sources to influence subsequent agent actions.
Sanitization: There is no evidence of sanitization or validation of the content retrieved from external URLs before it is processed by the agent.

api-tester