The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the user to execute shell commands to perform phone number scans and launch a web-based dashboard.
Evidence: Use of phoneinfoga scan, phoneinfoga serve, and shell loops to process files.
[EXTERNAL_DOWNLOADS]: The skill recommends obtaining the tool via GitHub releases or by pulling a Docker image from a remote registry.
Evidence: docker run --rm sundowndev/phoneinfoga.
[INDIRECT_PROMPT_INJECTION]: The skill describes a tool that ingests and processes data from untrusted external sources, such as Google search results and third-party APIs, which could theoretically contain instructions designed to influence the agent.
Ingestion points: Data retrieved from Google Dorks (LinkedIn, Facebook, etc.) and API responses from NumVerify.
Boundary markers: Absent. There are no instructions for the agent to use delimiters or ignore embedded instructions within search results.
Capability inventory: The skill utilizes shell execution, network access for OSINT, and file system writes for saving results.
Sanitization: Absent. The documentation does not specify methods for sanitizing or escaping the data gathered from the web before presentation or processing.

phoneinfoga