The Agent Skills Directory

[DATA_EXFILTRATION]: The skill communicates with an external endpoint defined by the NEXSCOPE_PROXY_BASE environment variable to retrieve e-commerce keyword data. It securely transmits the NEXSCOPE_API_KEY in the authorization header to authenticate requests to the vendor's infrastructure.
[COMMAND_EXECUTION]: The skill executes its primary logic via a Python script (scripts/keyword_reverse_lookup.py) using the Bash tool to process data and generate reports.
[EXTERNAL_DOWNLOADS]: The skill utilizes standard third-party libraries for generating analytical charts.
Dependencies include matplotlib, numpy, and Pillow.
The documentation also suggests the use of the adjustText library for optimizing label placement.
[PROMPT_INJECTION]: The skill processes external data from a proxy API, which presents a surface for indirect prompt injection.
Ingestion points: Data is ingested from the NexScope Proxy API via the js_api_call function in scripts/keyword_reverse_lookup.py.
Boundary markers: The skill does not implement specific delimiters or 'ignore' instructions for the data being interpolated into the final report.
Capability inventory: The skill is permitted to use Bash, Read, and Write tools as specified in the SKILL.md frontmatter.
Sanitization: While the script validates that the API response is valid JSON, it does not perform semantic sanitization of the keyword strings before including them in the markdown output.

keyword-reverse-lookup