speckit-checklist
Warn
Audited by Gen Agent Trust Hub on Aug 7, 2026
Risk Level: MEDIUMCOMMAND_EXECUTIONREMOTE_CODE_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill dynamically identifies and triggers commands defined in the project's .specify/extensions.yml file. It uses the EXECUTE_COMMAND directive to run hooks defined in hooks.before_checklist and hooks.after_checklist.
- [REMOTE_CODE_EXECUTION]: The execution flow involves running a shell script at .specify/scripts/bash/check-prerequisites.sh. This represents a potential risk if the skill is used within a repository containing untrusted scripts.
- [DATA_EXFILTRATION]: The skill ingests sensitive feature documentation including spec.md, plan.md, and tasks.md. While the primary purpose is checklist generation, this access provides a surface for data exposure if combined with the command execution hooks.
- [PROMPT_INJECTION]: The skill has an indirect prompt injection surface. Ingestion points: .specify/extensions.yml and project markdown files. Boundary markers: Absent. Capability inventory: Command execution via EXECUTE_COMMAND and local script execution. Sanitization: Basic shell escaping for arguments.
Audit Metadata