cheat-sheet-guide

Pass

Audited by Gen Agent Trust Hub on Feb 18, 2026

Risk Level: SAFE
Full Analysis
  • Prompt Injection (SAFE): The instructions are strictly focused on documentation tasks. No attempts to override safety filters, extract system prompts, or bypass constraints were detected.
  • Data Exposure & Exfiltration (SAFE): The skill reads configuration file paths and code patterns within the project directory. It does not attempt to access sensitive user directories (~/.ssh, ~/.aws) or use network tools (curl, wget) to send data externally.
  • Indirect Prompt Injection (LOW): The skill possesses a vulnerability surface as it ingests untrusted data from the local project files.
  • Ingestion points: The agent is instructed to 'Search the codebase' and 'Examine the Project' (SKILL.md, Step 2).
  • Boundary markers: No specific delimiters or instructions are provided to the agent to ignore instructions embedded in the project files.
  • Capability inventory: The skill only generates text output; it has no network, file-write, or command execution capabilities.
  • Sanitization: No sanitization or validation of the codebase content is performed before generating the cheat sheet.
  • Unverifiable Dependencies & Remote Code Execution (SAFE): There are no package installations, remote script downloads, or dynamic execution patterns present in the instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 18, 2026, 04:01 AM