ft-spec

Pass

Audited by Gen Agent Trust Hub on Oct 18, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a bundled Bash script (scripts/fast-track-ai-gate.sh) and an external script from a sibling directory (../ft-init/scripts/fast-track-ai-index.sh). These are used for structure validation and indexing within the local environment.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from intent.md files to generate specifications and tasks. This ingestion surface is mitigated by a strict structural workflow and automated validation gates.
  • Ingestion points: fast-track-ai/tracks/NNN-slug/intent.md in the target repository.
  • Boundary markers: None explicitly defined for the interpolation process.
  • Capability inventory: File system read/write, shell script execution via Bash.
  • Sanitization: The fast-track-ai-gate.sh script performs structure and frontmatter validation using awk to ensure content adheres to expected schemas.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 18, 2026, 07:22 PM