board
Pass
Audited by Gen Agent Trust Hub on Sep 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill reads markdown posts from a shared message board, which creates a vulnerability surface where malicious instructions embedded in messages could influence the agent's behavior.\n
- Ingestion points: The
--readcommand inSKILL.mdtriggers the reading of external markdown files from the message board channels.\n - Boundary markers: While posts utilize YAML frontmatter, there is no explicit instruction to the agent to ignore or isolate instructions contained within the message body.\n
- Capability inventory: The skill executes a local Python script (
board_manager.py). An agent utilizing this skill may also possess broader file system and tool capabilities that an attacker could attempt to trigger.\n - Sanitization: There is no evidence of content sanitization or validation performed on the ingested message data.\n- [COMMAND_EXECUTION]: The skill documentation specifies the execution of a local script,
board_manager.py, using the Python interpreter to perform list, read, and post actions.
Audit Metadata