board-meeting
Pass
Audited by Gen Agent Trust Hub on Sep 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill reads the contents of
HUMAN_AGENDA.mdand all files within thedocs/directory to facilitate a "board meeting" workflow, creating a surface for indirect prompt injection.\n - Ingestion points:
SKILL.mdspecifies readingHUMAN_AGENDA.mdand all files indocs/during the "On Load" and "Meeting Structure" phases, which are passed into the context of sub-agents.\n - Boundary markers: There are no explicit instructions or delimiters used to separate the content of these files from the agent's instructions, nor are there warnings to ignore potential instructions embedded within them.\n
- Capability inventory: The skill has the ability to write to files (updating
HUMAN_AGENDA.mdand deliverables) and to spawn sub-agents using theTasktool withsubagent_type: "general-purpose".\n - Sanitization: No sanitization, validation, or filtering of the content read from these files is mentioned before the data is processed or used for agent decisions.
Audit Metadata