skills/leandrocfe/skills/code-review/Gen Agent Trust Hub

code-review

Pass

Audited by Gen Agent Trust Hub on Aug 10, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill constructs and executes shell commands such as git diff <ponto-fixo>...HEAD using a user-supplied reference point. While the skill includes a validation step using git rev-parse, the direct interpolation of user input into a shell command remains a potential vector for command injection depending on the platform's tool execution constraints.\n- [PROMPT_INJECTION]: The skill is susceptible to Indirect Prompt Injection (Category 8) because it ingests untrusted content and processes it via sub-agents without isolation.\n
  • Ingestion points: Content retrieved via git diff, git log, and various specification files (e.g., from docs/, specs/, or an external issue tracker).\n
  • Boundary markers: The skill fails to define clear boundary markers or provide instructions to the sub-agents to ignore embedded commands within the analyzed data.\n
  • Capability inventory: The skill possesses the ability to execute shell commands and invoke the Agent tool for sub-tasking.\n
  • Sanitization: No sanitization, filtering, or escaping is performed on the code changes or documentation before they are interpolated into the sub-agent prompts.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 10, 2026, 08:22 PM
Security Audit — agent-trust-hub — code-review