brainstorm
Pass
Audited by Gen Agent Trust Hub on Mar 9, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill features a surface for indirect prompt injection as it is designed to ingest and process content from potentially untrusted codebase files.
- Ingestion points: The skill reads project documentation (README.md), configuration files (package.json), and scans project issues and pull requests to gather context.
- Boundary markers: There are no specified delimiters or instructions to ignore potential commands embedded within the data being read from these files.
- Capability inventory: The skill uses Read, Glob, Grep, and Write tools to analyze the project and generate a Brainstorm Report.
- Sanitization: No logic is provided to sanitize or validate the content of the ingested files before they are processed by the agent.
- [SAFE]: The skill does not request sensitive permissions, perform remote code execution, or use obfuscation techniques. All external links point to legitimate documentation and the author's own repository.
Audit Metadata