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.sh to 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.sh path.
  • Sanitization: There is no evidence of validation or sanitization for the inputs retrieved from the pull request or project configuration files.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 30, 2026, 09:09 PM
Security Audit — agent-trust-hub — speckit-review-tests