e2e-reviewer

Pass

Audited by Gen Agent Trust Hub on Oct 22, 2026

Risk Level: SAFECOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [DYNAMIC_EXECUTION]: The skill's internal logic utilizes dynamic execution patterns to optimize its analysis engine. In scripts/scope-worker.py and scripts/scope-graph.py, the skill uses Python's importlib.util to load its own sub-modules from the file system. Additionally, scripts/scope-watch.py uses ctypes.CDLL to interface with the macOS system library /usr/lib/libSystem.B.dylib for local APFS filesystem probing (fstatfs64). These operations are used to manage complex graph traversals and file monitoring during the review process.
  • [COMMAND_EXECUTION]: The skill automates complex analysis tasks by executing shell commands. The script scripts/scope-graph.py spawns a subprocess to run the bundled scripts/scope-source.sh helper. Furthermore, the SKILL.md instructions guide the AI agent to use standard system tools such as rg, sed, and nl for targeted reading and filtering of the code being reviewed.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted code from target repositories, which inherently presents an indirect prompt injection surface. However, the skill implements a comprehensive defense-in-depth approach:
    • Ingestion points: Repository files (Playwright/Cypress specs, Page Objects, and configurations) are read into the agent's context as instructed in SKILL.md using rg and sed.
    • Boundary markers: The SKILL.md contains a mandatory "Untrusted-input boundary" section that explicitly instructs the agent to treat all target repository content as data, never as instructions, and to ignore any commands embedded in comments or strings.
    • Capability inventory: The skill uses its own bundled analysis scripts (scan.sh), system utilities, and internal Python scripts for lexing and scope tracking.
    • Sanitization: The instructions prohibit the agent from quoting or propagating suspected prompt-injection text in its generated findings.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 22, 2026, 01:03 PM