The Agent Skills Directory

[SAFE]: The skill communicates exclusively with SalesLoft's official API domain (api.salesloft.com), which is a well-known and trusted service provider in the sales industry.
[SAFE]: Sensitive authentication tokens are managed using process.env.SALESLOFT_API_KEY. Using environment variables is the recommended secure practice for secret management, and no hardcoded credentials were found.
[INDIRECT_PROMPT_INJECTION]: The skill serves as a surface for processing external data from SalesLoft API responses (such as email subjects and call notes) which could theoretically contain untrusted instructions.
Ingestion points: Data is ingested through REST API endpoints like /activities/emails.json and /activities/calls.json in SKILL.md.
Boundary markers: None are present in the code snippets.
Capability inventory: The skill uses axios for network requests and logs results to the console. While Bash and Write are allowed in the frontmatter, they are not utilized in the provided scripts to process external data.
Sanitization: There is no explicit sanitization of the retrieved data, but as the data is only being logged, the risk is negligible.

salesloft-core-workflow-b