brainstorming
Pass
Audited by Gen Agent Trust Hub on Nov 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read the current project state, including files, documentation, and recent commits. This creates a surface where malicious instructions embedded in the codebase or commit history could influence the agent's behavior during the brainstorming process.
- Ingestion points: Project files, documentation, and git commit history (brainstorming/SKILL.md).
- Boundary markers: Absent; the skill does not explicitly instruct the agent to disregard instructions found within the project data.
- Capability inventory: The skill utilizes file-writing capabilities to save design documents and git commands for version control and workspace management (brainstorming/SKILL.md).
- Sanitization: Absent; no specific sanitization or validation of the ingested project data is described.
- [COMMAND_EXECUTION]: The skill guides the agent to perform git operations such as committing design documents and creating isolated workspaces using
git worktrees. These are standard development tasks but involve executing shell commands as part of the intended workflow.
Audit Metadata