gs-blast-radius

Pass

Audited by Gen Agent Trust Hub on Nov 20, 2026

Risk Level: SAFEDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [DYNAMIC_EXECUTION]: The skill instructions in Step 5 require the agent to 'Write a script or test that runs the real code, run it, and paste what happened' to verify the safety of a change. This involves the runtime generation and execution of arbitrary code within the user's environment.
  • [INDIRECT_PROMPT_INJECTION]: The skill defines an attack surface for indirect prompt injection by processing untrusted data. 1. Ingestion points: Step 1 instructions direct the agent to retrieve the PR body, discussion, and commits using gh pr view and git log. 2. Boundary markers: There are no instructions providing delimiters or warnings to ignore embedded commands within the ingested PR data. 3. Capability inventory: The skill has the capability to execute shell commands (git, gh) and to perform dynamic code execution in Step 5. 4. Sanitization: No input sanitization or validation is specified for the data ingested from external version control sources.
  • [COMMAND_EXECUTION]: The skill uses shell-based tools including git log, git blame, and gh pr view to gather context about the codebase and pull requests.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 20, 2026, 09:35 AM