algolia-rate-limits
Pass
Audited by Gen Agent Trust Hub on Sep 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to capture and interpret external data from Algolia API responses, including error messages and request metadata, creating a surface for potential instruction injection if the data source is compromised or manipulated.
- Ingestion points: The skill instructions (SKILL.md) direct the agent to "Capture the failing operation, response, request ID, client version" when handling rate limits.
- Boundary markers: The instructions do not define explicit boundary markers or "ignore embedded instructions" warnings for the captured response data.
- Capability inventory: The skill is granted
WriteandEdittool permissions, which could be leveraged to modify local code or configuration based on the content of processed API responses. - Sanitization: There are no explicit requirements for sanitizing, validating, or filtering the external response content before the agent interprets it.
Audit Metadata