The Agent Skills Directory

[COMMAND_EXECUTION]: Utilizes python3 to parse credentials from a configuration file and curl to perform network requests for lead discovery and enrichment.
[PROMPT_INJECTION]: Contains a vulnerability surface for indirect prompt injection where untrusted external data could influence the agent's behavior.
Ingestion points: Lead and company data entering through the lead_info, target_company, research_plan, and people_focus_prompt parameters in SKILL.md.
Boundary markers: No delimiters or protective instructions are used to separate user-provided data from system prompts.
Capability inventory: Includes network communication via curl to external API endpoints (SKILL.md).
Sanitization: No input validation or sanitization is performed on user-supplied fields before transmission to the API.
[DATA_EXFILTRATION]: Accesses the local ~/.gooseworks/credentials.json file to retrieve API keys. While this is for legitimate vendor authentication, the skill interacts with sensitive local files to manage its identity.
[EXTERNAL_DOWNLOADS]: Instructs the user to use npx for installation and authentication tasks, which involves fetching and executing code from the npm registry.

lead-enrichment-sixtyfour