speckit-clarify
Warn
Audited by Gen Agent Trust Hub on Jul 30, 2026
Risk Level: MEDIUMCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill is instructed to execute a local shell script at
.specify/scripts/bash/check-prerequisites.shto obtain project paths and configuration details. - [COMMAND_EXECUTION]: The skill implements a dynamic hook system that reads
.specify/extensions.ymland executes commands defined in thehooks.before_clarifyandhooks.after_clarifysections. This allows for the execution of arbitrary commands based on strings provided in project-level configuration files. - [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface due to its reliance on multiple unsanitized external files from the project repository.
- Ingestion points: Reads and processes
.specify/extensions.yml,.specify/memory/constitution.md, the feature specification file, andFEATURE_DIR/checklists/requirements.md. - Boundary markers: Absent. The agent is directed to treat the contents of these files as authoritative instructions or context without delimiters.
- Capability inventory: The skill can execute local scripts, invoke dynamic hook commands, and perform writes to the local file system.
- Sanitization: No filtering, escaping, or validation logic is specified for the content ingested from the external project files.
Audit Metadata