Skills
Navigate
skills/jotafurtado/fast-track-ai/fast-track-ai-spec/Gen Agent Trust Hub

fast-track-ai-spec

Pass

Audited by Gen Agent Trust Hub on Oct 14, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the repository's 'intent.md' file to generate specifications, tasks, and architectural decisions.
  • Ingestion points: Reads fast-track-ai/tracks/NNN-slug/intent.md to classify questions and define project scope.
  • Boundary markers: There are no explicit instructions to use delimiters or ignore instructions embedded within the source data.
  • Capability inventory: The skill possesses file-writing capabilities (for spec.md, tasks.md, decisions.md, and INDEX.md) and executes local maintenance scripts.
  • Sanitization: The instructions do not define methods for sanitizing or escaping content from the intent file before interpolation into new documents or tasks.
  • [COMMAND_EXECUTION]: The skill executes scripts for project indexing and structure validation.
  • Evidence: The skill runs ../fast-track-ai-init/scripts/fast-track-ai-index.sh and ./scripts/fast-track-ai-gate.sh to maintain the project state and ensure structural integrity.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 14, 2026, 04:33 PM