cs-brainstorm

Pass

Audited by Gen Agent Trust Hub on May 1, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill facilitates an indirect prompt injection surface by summarizing user input from brainstorming sessions and writing it to {slug}-brainstorm.md files. These files are intended for consumption by downstream skills like cs-feat-design, creating a vector where malicious user content could influence subsequent agent actions. \n
  • Ingestion points: User input provided during the brainstorming and triage dialogue as described in SKILL.md.\n
  • Boundary markers: No explicit delimiters or instructions are provided to separate untrusted user content from architectural or design requirements in the generated files.\n
  • Capability inventory: The skill utilizes glob, grep, and file system read/write operations (as described in SKILL.md) to manage project documentation.\n
  • Sanitization: There is no evidence of sanitization or validation of the user's input before it is summarized and persisted to the file system.\n- [COMMAND_EXECUTION]: The skill performs file system management tasks including directory creation (mkdir) and file writing based on user-supplied strings (slug) for project organization.
Audit Metadata
Risk Level
SAFE
Analyzed
May 1, 2026, 03:33 AM