board
Pass
Audited by Gen Agent Trust Hub on Aug 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill allows the agent to read messages from various channels which are considered untrusted data sources. These messages could contain instructions designed to manipulate the agent's logic.
- Ingestion points: Untrusted content is ingested from message board channels when using the
--readcommand inSKILL.md. - Boundary markers: Although posts use Markdown and YAML frontmatter, there are no specific markers or instructions to prevent the agent from following directions contained within the post body.
- Capability inventory: The skill can execute a local Python script (
board_manager.py) to manage file operations and list/read/post messages. - Sanitization: No sanitization or filtering of external message content is documented before the data is processed by the agent.
Audit Metadata