spec-kit-reconcile
Pass
Audited by Gen Agent Trust Hub on Apr 13, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill runs a local shell script located at
scripts/check-prerequisites.shwith specific flags to resolve file paths and repository status. - [PROMPT_INJECTION]: The skill incorporates untrusted data from user-supplied gap reports and repository files into the agent's context, creating an indirect prompt injection surface.
- Ingestion points: Processes user-provided 'gap reports' and existing repository files such as
spec.md,plan.md,tasks.md, andmemory/constitution.md. - Boundary markers: The instructions do not define any delimiters or safety markers to separate ingested content from system instructions.
- Capability inventory: The skill is capable of executing a local shell script and performing write operations on repository artifacts.
- Sanitization: There is no evidence of input sanitization or validation of the text content before it is processed by the agent.
Audit Metadata