The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to fetch and parse content from external, untrusted blog URLs and RSS feeds, creating a surface for indirect prompt injection.
Ingestion points: The discover_feed_url and parse_feed functions in scripts/scrape_blogs.py fetch HTML and XML content directly from user-provided or discovered URLs.
Boundary markers: There are no delimiters or specific instructions to the agent to ignore or treat the scraped content as untrusted data.
Capability inventory: The skill has the capability to perform network requests and output processed data to the agent's context, which could be leveraged if the agent follows instructions hidden in the scraped content.
Sanitization: No sanitization or filtering is performed on the scraped text (title, description, content) beyond standard XML parsing.
[CREDENTIALS_UNSAFE]: The script handles the GOOSEWORKS_API_KEY by passing it as a query parameter in network requests to the Apify proxy endpoint.
Evidence: In scripts/scrape_blogs.py, the scrape_apify function uses params={"token": token} in requests.post and requests.get calls. Transmitting credentials in URL query parameters is a security risk as they may be logged by intermediate proxies or server logs.

blog-scraper