The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill uses npx to fetch and run the @vibeprospecting/vpai@latest package from the npm registry. This practice involves downloading and executing unversioned code from an external source at runtime.
[COMMAND_EXECUTION]: The skill executes several shell commands to manage the outreach workflow. This includes running npx for prospecting, curl for interacting with the Lemlist API (e.g., verifying credentials and managing campaigns), and python3 for data parsing and script execution.
[DYNAMIC_EXECUTION]: The skill contains embedded Python code for both small tasks and complex operations. It uses python3 -c to parse JSON output from API calls and includes a substantial multi-line Python script utilizing the requests library to upload prospect data to Lemlist campaigns.
[INDIRECT_PROMPT_INJECTION]: The skill processes prospect data (firmographics, LinkedIn profiles, etc.) retrieved from an external tool and interpolates it into prompts for email generation.
Ingestion points: Data is read from the prospects-enriched.csv file generated in Phase 2.
Boundary markers: The skill does not define explicit delimiters or instructions for the agent to ignore potentially malicious content within the fetched data.
Capability inventory: The skill has the ability to execute shell commands, write to the filesystem, and perform network requests via Python.
Sanitization: There is no evidence of data validation or escaping before the prospect information is used to generate personalized emails.

cold-email-lemlist