workflow-brainstorm
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the command
git log -n 10 --onelineto gather context on recent project activity. This is a limited, read-only command used for the skill's primary purpose. - [INDIRECT_PROMPT_INJECTION]: The skill processes project-level documentation and configuration files, which presents a surface for indirect prompt injection if those files contain malicious instructions.
- Ingestion points: Reads
README.md,docs/content,design-system.md, and dependency manifests likepackage.json,Cargo.toml, orpyproject.toml. - Boundary markers: No specific boundary markers or instruction-ignoring prompts are used when reading project context.
- Capability inventory: The skill is designed to read file structures, read documentation content, execute git log commands, and write design specifications to the local file system.
- Sanitization: The skill does not perform sanitization on the content of the project files it reads before processing them.
Audit Metadata