brainstorm-with-file
Pass
Audited by Gen Agent Trust Hub on Mar 2, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a local shell command to identify the environment context.
- Evidence: The script runs
git rev-parse --show-toplevelto determine the project root directory for saving workflow artifacts. - [PROMPT_INJECTION]: User-supplied data is interpolated into instructions for subagents, creating a surface for indirect prompt injection.
- Ingestion points: The
TOPICargument provided by the user and the codebase context gathered via grep/glob inStep 2.1are both used to build subagent prompts. - Boundary markers: The skill uses Markdown headers (e.g.,
## Task,## Context) to separate instructions from data, but lacks explicit "ignore embedded instructions" guards. - Capability inventory: The skill can read local files, write JSON/Markdown artifacts, and spawn additional agents with new instructions.
- Sanitization: No sanitization or escaping is performed on the
${idea_or_topic}or${explorationContext}variables before they are inserted into the JavaScript templates forspawn_agentcalls.
Audit Metadata