The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes the orth run command-line utility to interact with external enrichment services. This is consistent with the vendor's (orthogonal-sh) infrastructure and the skill's stated purpose.
[DATA_EXFILTRATION]: The skill transmits lead information, including email addresses and names, to the Sixtyfour and Apollo APIs. While this involves sending user data to external endpoints, it is the primary and intended function of an enrichment skill.
[INDIRECT_PROMPT_INJECTION]: The skill processes data retrieved from web-browsing agents (Sixtyfour), which constitutes an indirect prompt injection surface. However, the risk is inherent to the use-case of processing live web data.
Ingestion points: JSON responses from Sixtyfour /enrich-lead and /enrich-company endpoints in SKILL.md.
Boundary markers: Absent; data is merged directly into the final JSON output.
Capability inventory: Subprocess execution via orth run.
Sanitization: No explicit sanitization is performed on the data returned from external sources before being processed by the agent.

gtm-enrichment-deep