build-by-story

Pass

Audited by Gen Agent Trust Hub on Sep 5, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from tasks.md and requirements.md to drive agent behavior, partition work, and schedule tasks.
  • Ingestion points: Reads tasks.md and requirements.md to perform deterministic derivation of task units (referenced in SKILL.md and story-unit-mode.md).
  • Boundary markers: The skill records a content hash of 'Global Constraints' at setup to prevent unauthorized plan modification and enforces an 'Iron Law' human-in-the-loop gate before proceeding between units.
  • Capability inventory: Performs file writes to the .skills/ directory and tasks.md, executes shell commands via git, and orchestrates sub-agents for implementation and review.
  • Sanitization: Uses structured parsing for specific identifiers (e.g., **CODE-N.M**) and topological sorting rather than interpreting freeform natural language for logic derivation.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 5, 2026, 03:13 AM
Security Audit — agent-trust-hub — build-by-story