ql-review

Warn

Audited by Gen Agent Trust Hub on Mar 25, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes python -c "import main_module" to verify imports during the integration review stage. This results in the execution of any top-level code or initialization logic within the specified module. If the code being reviewed is untrusted or malicious, this provides a vector for code execution on the host system.
  • [COMMAND_EXECUTION]: The skill relies on shell commands like git merge-base and grep to perform repository analysis and code searches.
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it ingests and processes untrusted content from source code and product requirement documents (PRDs).
  • Ingestion points: Files like quantum.json, PRDs, and source code files are read into the agent's context.
  • Boundary markers: The instructions do not define delimiters or specific warnings to ignore instructions found within the reviewed data.
  • Capability inventory: The agent can execute shell commands and Python code.
  • Sanitization: There is no evidence of content sanitization or validation of the data retrieved from external files before it is used to drive the review logic.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 25, 2026, 02:58 AM