brave-man
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill implements a workflow where user-supplied answers are interpolated into a
prompt.mdfile intended to serve as the system instructions for a subsequent agent session.\n - Ingestion points: User responses gathered during the eight phases of the project interview defined in
SKILL.md.\n - Boundary markers: The skill uses markdown headers to structure the output file, but does not specify delimiters or warnings to prevent user-supplied data from being interpreted as instructions by the downstream agent.\n
- Capability inventory: The skill is restricted to conversational requirements gathering and local file writing (
prompt.md); it does not possess network access, subprocess execution, or dynamic code evaluation capabilities.\n - Sanitization: The instructions do not mandate sanitizing, escaping, or validating user input before it is written to the specification file.
Audit Metadata