clari-upgrade-migration
Pass
Audited by Gen Agent Trust Hub on Sep 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from the Clari API (e.g., via
curland Python logic). While this represents a potential attack surface for indirect prompt injection if the remote data source were compromised, the skill mitigates this risk by explicitly instructing the user to keep live credentials and raw forecast values out of the final migration receipt. - Ingestion points: Data returned from
https://api.clari.com/v4/export/forecast/list. - Boundary markers: The skill recommends using an 'approved compatibility baseline' and 'representative non-production exports' for testing.
- Capability inventory: Uses
curl,jq, and standard Python dictionary operations. - Sanitization: The instructions explicitly mandate the redaction of raw forecast values and credentials from outputs.
- [SAFE]: The skill uses
CLARI_API_KEYas an environment variable rather than hardcoding credentials, which is a standard security best practice. - [SAFE]: All external URLs point to legitimate documentation and API endpoints for Clari, a well-known revenue intelligence service.
Audit Metadata