review

Pass

Audited by Gen Agent Trust Hub on Mar 5, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because its core function is to analyze untrusted data in the form of source code from pull requests, branches, or commits.
  • Ingestion points: Source code and metadata are ingested from external repositories in Phase 1 (Setup and Context Gathering) and Phase 2 (Parallel Agent Reviews).
  • Boundary markers: No explicit delimiters or instructions are provided to the agent to distinguish between code-to-be-analyzed and potential instructions embedded within that code.
  • Capability inventory: The skill utilizes powerful tools including 'Bash', 'Write', and 'Task', which could be targeted by successful injection.
  • Sanitization: There is no evidence of input validation or sanitization for the code being reviewed.
  • [COMMAND_EXECUTION]: The skill uses the 'Bash' tool to perform environment setup tasks such as 'git-worktree'. While standard for the use case, this capability allows for local system interaction based on inputs derived from untrusted code contexts.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 5, 2026, 08:18 AM