brainstorm
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection via user-supplied session files.
- Ingestion points: In
SKILL.md, the agent is instructed to ask the user to 'upload/provide the latest version file' when continuing an existing project. - Boundary markers: There are no defined delimiters or 'ignore embedded instructions' warnings for the agent when processing these external project files.
- Capability inventory: The skill has the capability to read and write markdown files within the
brainstorms/directory and is specifically directed to 'surface connections' between different projects in 'connected mode', creating a vector for cross-project data exposure if an injection occurs. - Sanitization: The skill lacks logic to sanitize, validate, or filter the content of the ingested files before it is incorporated into the active brainstorming context.
Audit Metadata