The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill interacts with the Clari API endpoint (api.clari.com) to manage export jobs. This communication is required for the skill's primary purpose and targets a well-known SaaS provider.
Evidence: The Python function poll_with_backoff in SKILL.md uses requests.get to poll https://api.clari.com/v4/export/jobs/{job_id}.
[PROMPT_INJECTION]: The skill ingests data from the external Clari API, which serves as a potential surface for indirect prompt injection, though the risk is minimal given the context of job status monitoring.
Ingestion points: The resp.json() call in SKILL.md parses responses from the Clari API.
Boundary markers: There are no explicit delimiters or warnings to ignore instructions within the API response.
Capability inventory: The skill uses network operations via the requests library to interact with the API.
Sanitization: The API response is returned as a dictionary without explicit sanitization, which is standard for status-checking utilities.

clari-rate-limits