brainstorming
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill has a vulnerability surface for indirect prompt injection by ingesting untrusted data from the project environment.
- Ingestion points: The skill instructions in
SKILL.mddirect the agent to "Check out the current project state first (files, docs, recent commits)" at the start of a brainstorming session. - Boundary markers: There are no explicit boundary markers or instructions to treat project content as untrusted data or to ignore embedded commands within those files.
- Capability inventory: The skill possesses file-write capabilities (writing design documents to
docs/plans/), git interaction (committing the design document), and the ability to trigger downstream implementation skills (git worktrees and implementation plans). - Sanitization: No sanitization or validation of the ingested project data is described before it is used to influence the design and implementation process.
Audit Metadata