battleship-brainstorm

Pass

Audited by Gen Agent Trust Hub on Feb 28, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill defines an indirect prompt injection surface by instructing the agent to read and incorporate content from various local files into its brainstorming logic.
  • Ingestion points: The agent reads all files within a context/ folder and specifically looks for problem-framing.md, hmw-opportunities.md, and dot-vote-*.md.
  • Boundary markers: The instructions do not define delimiters or provide warnings to the LLM to ignore instructions that may be embedded within these external files.
  • Capability inventory: The skill's capabilities are limited to reading from and writing to the local filesystem (e.g., creating battleship-brainstorm.md). It does not contain network request functions, shell command execution, or dynamic code evaluation.
  • Sanitization: There is no evidence of input validation, filtering, or escaping of the content retrieved from the workspace files before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 28, 2026, 03:25 AM