architecture-md-builder
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill uses exploration agents to process the project's codebase to synthesize architectural documentation. This introduces a surface where instructions embedded in the source code could potentially influence the agent's output during the synthesis phase.\n
- Ingestion points: Project source files read during codebase exploration (Phase 2) and verification (Phase 4).\n
- Boundary markers: The skill does not explicitly define delimiters for untrusted code content in its prompts.\n
- Capability inventory: Spawning sub-agents with 'Explore' type and writing the final ARCHITECTURE.md file.\n
- Sanitization: No specific sanitization or filtering of codebase content is documented.\n- [COMMAND_EXECUTION]: The skill utilizes shell commands like
wc -lfor file size analysis andpython3to execute a local research script (exa_search.py). These operations are consistent with the skill's purpose of mapping and documenting a project.
Audit Metadata