speckit-tasks

Pass

Audited by Gen Agent Trust Hub on Mar 13, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: Executes a local bash script (.specify/scripts/bash/check-prerequisites.sh) to discover project metadata and available documentation.
  • [PROMPT_INJECTION]: The skill ingests data from external project documents such as plan.md, spec.md, and data-model.md, creating a surface for indirect prompt injection.
  • Ingestion points: Multiple Markdown documents within the project's FEATURE_DIR are read and processed.
  • Boundary markers: There are no explicit delimiters or instructions provided to the agent to ignore potentially malicious content within these files.
  • Capability inventory: The skill possesses file system write access and the ability to execute local shell scripts.
  • Sanitization: The contents of the documents are used directly to drive the task generation logic without validation or sanitization.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 13, 2026, 06:47 PM