speckit-review-run

Pass

Audited by Gen Agent Trust Hub on Jul 30, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a project-local bash script located at .specify/scripts/bash/detect-changed-files.sh to determine the scope of the code review. This is an expected behavior for a tool integrated with the spec-kit framework and is used for metadata collection (changed file list).
  • [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection by processing external data and executing commands based on that data.
  • Ingestion points: File content from .specify/extensions/review/review-config.yml, JSON output from the .specify/scripts/bash/detect-changed-files.sh script, and user-supplied $ARGUMENTS.
  • Boundary markers: The instructions do not define explicit delimiters to isolate untrusted data from the instruction context.
  • Capability inventory: The skill has the capability to execute local bash scripts and trigger multiple specialized sub-agents.
  • Sanitization: There is no evidence of validation or sanitization for the data ingested from the project repository or user input.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 30, 2026, 09:10 PM
Security Audit — agent-trust-hub — speckit-review-run