brainstorming
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to ingest and analyze project-specific data which represents a surface for indirect prompt injection.
- Ingestion points: In SKILL.md, the agent is directed to 'Check out the current project state first (files, docs, recent commits)' to understand user intent.
- Boundary markers: The instructions do not specify the use of delimiters or boundary markers to isolate untrusted project data from the agent's core instructions.
- Capability inventory: The skill has the capability to write design documents to the filesystem under 'docs/plans/' and perform git operations including commits and worktree creation.
- Sanitization: There are no explicit instructions provided for the sanitization, filtering, or validation of the ingested project data.
Audit Metadata