exa-rate-limits
Pass
Audited by Gen Agent Trust Hub on Sep 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill includes logic to process and aggregate data from the Exa API, which is an external and untrusted source of content.\n
- Ingestion points: The skill ingests data via
exa.searchAndContentscalls in Step 1, Step 2, and Step 4 of theSKILL.mdfile.\n - Boundary markers: No explicit boundary markers or delimiters are suggested to separate external content from system instructions in the provided implementation examples.\n
- Capability inventory: The skill is configured with
Read,Write, andEdittools in the YAML frontmatter, which provides a capability surface if the agent is influenced by embedded instructions in search results.\n - Sanitization: The provided code examples lack sanitization or filtering of the content returned by the API before it is processed or used by the agent.
Audit Metadata