speckit-clarify

Warn

Audited by Gen Agent Trust Hub on Oct 12, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a local shell script located at .specify/scripts/bash/check-prerequisites.sh during the initialization phase to retrieve project metadata.
  • [DYNAMIC_EXECUTION]: The skill implements a hook system that reads commands from .specify/extensions.yml and executes them via EXECUTE_COMMAND. This allows the execution of arbitrary shell commands defined in the project configuration before and after the clarification workflow.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from the feature specification file and user arguments without sanitization or boundary markers, creating a surface for embedded instructions to influence agent behavior. 1. Ingestion points: .specify/extensions.yml, FEATURE_SPEC, and user arguments. 2. Boundary markers: None identified. 3. Capability inventory: Executes local bash scripts, executes dynamic hook commands, and writes to the filesystem. 4. Sanitization: No explicit validation or escaping of input is performed.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Oct 12, 2026, 03:24 PM