The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and summarize data from external public sources (SSL certificates, USPTO trademark filings, FCC registrations, and FDA records). These sources are untrusted and could contain malicious instructions or adversarial content designed to influence the agent's downstream actions.
Ingestion points: Data enters the agent's context through the output of the webcertificates, us-trademarks, fcc, and fda commands.
Boundary markers: The instructions do not specify any boundary markers (e.g., XML tags or delimiters) to separate the untrusted search results from the agent's instructions.
Capability inventory: The skill uses a bash tool to execute commands and jq to parse results. While the listed tools are for searching, a shell environment provides broad capabilities.
Sanitization: No explicit sanitization or filtering of the external data is mentioned before it is processed by the agent.
[COMMAND_EXECUTION]: The skill's primary mechanism is the execution of shell commands (bash) to run specialized programs. This creates a reliance on a high-privilege tool to perform its tasks.
[EXTERNAL_DOWNLOADS]: The skill instructs the user on how to install external plugins and connect to a remote MCP server (mcp.hedwigai.com). These resources are hosted by the skill's author and represent the intended infrastructure for the skill's functionality.

launch-signals