clari-rate-limits
Pass
Audited by Gen Agent Trust Hub on Sep 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external API responses, which introduces a surface for indirect prompt injection if the remote source is compromised.
- Ingestion points: Data from the Clari API is ingested via
resp.json()in thepoll_with_backofffunction inSKILL.md. - Boundary markers: There are no explicit delimiters or instructions provided to the agent to treat the API response data as untrusted or to ignore instructions embedded within it.
- Capability inventory: The agent is granted
Read,Write, andEdittools, and the provided scripts utilize therequestslibrary for network operations. - Sanitization: The logic validates specific status strings (e.g., "COMPLETED", "FAILED") but does not perform general sanitization of the JSON payload before it is returned to the agent context.
Audit Metadata