speckit-implement
Pass
Audited by Gen Agent Trust Hub on Sep 6, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a local prerequisite check script (.specify/scripts/bash/check-prerequisites.sh) and uses git commands to inspect the repository state.- [INDIRECT_PROMPT_INJECTION]: The skill ingests instructions from multiple local files to drive its behavior.
- Ingestion points: Files such as .specify/extensions.yml, tasks.md, plan.md, and checklists are read and parsed to determine the agent's next steps.
- Boundary markers: Absent. There are no explicit delimiters or instructions to ignore malicious content within the implementation data.
- Capability inventory: The skill can execute shell commands, invoke agent slash commands, and modify repository files.
- Sanitization: Content from the ingested files is used directly to influence execution flow without validation or escaping.- [DYNAMIC_EXECUTION]: The skill dynamically generates agent slash commands from hook identifiers found in .specify/extensions.yml. This allows the project configuration to dictate which agent capabilities are triggered during the implementation process.
Audit Metadata