speckit-baseline
Pass
Audited by Gen Agent Trust Hub on Mar 13, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: Executes a local bash script at .specify/scripts/bash/create-baseline.sh to retrieve project metadata.
- [PROMPT_INJECTION]: Susceptible to indirect prompt injection (Category 8).
- Ingestion points: The skill reads the entire codebase, including source code, configuration, and package files.
- Boundary markers: No delimiters or instructions are used to isolate codebase content from agent instructions.
- Capability inventory: Executes scripts, runs git commands, and writes files to the filesystem.
- Sanitization: No sanitization of analyzed file content is performed.
Audit Metadata