hive-tool-discovery
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill involves processing data from external providers and public APIs via tools like
fetch_public_apiandinvoke_api_endpoint. This creates an attack surface for instructions embedded in external data. - Ingestion points: External content is brought into the agent context in
SKILL.md(Procedure step 6) andreferences/discovery-surfaces.md(Surfaces table). - Boundary markers: The instructions explicitly mandate treating payloads as untrusted data and ignoring instructions within response text, serving as a prompt-level boundary.
- Capability inventory: The skill can perform network operations and stateful changes (writes), which are gated by schema validation and user consent.
- Sanitization: The skill employs schema inspection (
get_api_endpoint_schema) and result validation (validate_task_result) to ensure structural integrity of the data.
Audit Metadata