speckit-review-tests
Pass
Audited by Gen Agent Trust Hub on Jul 30, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute a local shell script at the path
.specify/scripts/bash/detect-changed-files.shto determine which files have changed, forbidding the use of standard git commands. - [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection attack surface because it processes untrusted data (pull request diffs and file contents) while possessing the capability to execute shell scripts.
- Ingestion points: Pull request file contents, change lists, and project-specific guidelines such as
.specify/memory/constitution.md. - Boundary markers: The instructions lack explicit delimiters or warnings to ignore instructions embedded within the processed pull request data.
- Capability inventory: Shell script execution via the hardcoded
.specify/scripts/bash/detect-changed-files.shpath. - Sanitization: There is no evidence of validation or sanitization for the inputs retrieved from the pull request or project configuration files.
Audit Metadata