The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests untrusted data from external sources and passes it to the agent for processing.
Ingestion points: The skill scrapes book titles, descriptions, and publisher names from Amazon search results via the bsr-scraper.py script and includes them in reports.
Boundary markers: There are no boundary markers or specific instructions implemented in the skill to isolate or ignore potential malicious instructions embedded in the scraped data.
Capability inventory: The skill has the capability to execute shell commands (python3), perform network requests via the requests library, and write data to the filesystem (/tmp).
Sanitization: No sanitization, escaping, or validation is performed on the scraped strings before they are presented to the agent for niche evaluation.
[EXTERNAL_DOWNLOADS]: The skill retrieves market and keyword data from several external services.
Fetches Amazon product data via the Apify API using a third-party scraper actor.
Retrieves search volume data from the DataForSEO API.
Accesses and scrapes data from public Amazon search and product pages.
[COMMAND_EXECUTION]: The skill executes local Python scripts to perform analysis and data retrieval.
Runs keyword-volume.py and bsr-scraper.py using keyword arguments supplied by the user.

niche-scout