gsd-map-codebase

Pass

Audited by Gen Agent Trust Hub on Apr 3, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8). It ingests untrusted data by analyzing an existing codebase to generate documentation.
  • Ingestion points: Analyzes files within the project codebase and accepts user-provided focus areas via {{GSD_ARGS}}.
  • Boundary markers: No specific delimiters or instructions to ignore embedded commands are defined for the analysis phase in the provided skill file.
  • Capability inventory: The skill can spawn multiple parallel sub-agents (gsd-codebase-mapper) and write documentation files to the .planning/codebase/ directory.
  • Sanitization: No explicit sanitization or validation of the codebase content is described before it is processed by the mapping agents.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 3, 2026, 04:33 AM