context-driven-development

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill provides a mechanism to analyze existing codebases and documentation to automatically generate project context artifacts. This creates an attack surface where malicious instructions embedded in a project's source code could influence the agent's behavior during the setup and scaffolding process.
  • Ingestion points: references/details.md mentions that for brownfield projects, the "System analyzes existing code, configs, and documentation".
  • Boundary markers: No explicit boundary markers or "ignore instructions" directives are specified for the parsing of existing code.
  • Capability inventory: The skill performs filesystem read operations to extract context and filesystem write operations to create artifacts in the conductor/ directory.
  • Sanitization: There is no mention of sanitization or validation of the content extracted from existing codebases before it is used to populate documentation.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 11:55 AM
Security Audit — agent-trust-hub — context-driven-development