speckit-clarify
Pass
Audited by Gen Agent Trust Hub on Jun 23, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill requires the execution of a local shell script located at
.specify/scripts/bash/check-prerequisites.sh. The instructions include specific guidance on shell escaping (e.g., handling single quotes in arguments) to ensure that parameters are passed safely to the underlying system.- [PROMPT_INJECTION]: The skill acts as a surface for indirect prompt injection because it reads and processes external feature specifications and user input. - Ingestion points: Content from
specs/<feature>/spec.mdand user answers during the clarification loop. - Boundary markers: The skill does not define explicit delimiters or 'ignore' instructions for the specification file content.
- Capability inventory: The agent has the ability to execute a local bash script and perform write operations to the
specs/directory. - Sanitization: The risk is mitigated by restricting user answers to multiple-choice options or very short phrases (maximum 5 words), which prevents the ingestion of complex malicious payloads.
Audit Metadata