shm-consumers
Pass
Audited by Gen Agent Trust Hub on Nov 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill describes an interface for receiving text-based messages from a producer via a reverse communication channel.
- Ingestion points: The 'on_message' callback in Python and 'ovstream_client_set_message_callback' in the C API (SKILL.md).
- Boundary markers: None mentioned for the text payload.
- Capability inventory: The documentation demonstrates simple logging ('print') of the received message.
- Sanitization: The protocol enforces a 16 MiB size limit and prohibits newline characters.
- [SAFE]: The skill consists of technical documentation for vendor-provided software, using consistent naming conventions and standard shared-memory implementation practices.
Audit Metadata