brainstorming

Pass

Audited by Gen Agent Trust Hub on Jun 26, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it is instructed to read the current project state, including files, documentation, and recent commits, which are untrusted inputs.
  • Ingestion points: Reads project files, documentation, and commit history to understand context (SKILL.md).
  • Boundary markers: The skill does not define clear delimiters or instructions to ignore embedded commands within the files it reads.
  • Capability inventory: The skill can write new design documents to the file system and perform git operations such as commits and worktree management.
  • Sanitization: No content validation or escaping is performed on the data ingested from the project files before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 26, 2026, 09:03 AM
Security Audit — agent-trust-hub — brainstorming