write-pad

Pass

Audited by Gen Agent Trust Hub on Mar 28, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted user data from the pad.md file and inline commands, which are used to guide the agent's behavior during the session.
  • Ingestion points: The agent reads the pad.md file at the project root and searches for source code files based on user-provided file paths and line numbers.
  • Boundary markers: The skill lacks explicit delimiters or instructions to ignore embedded commands within the data read from files.
  • Capability inventory: The agent's capabilities are limited to reading local files and writing to the pad.md file. It is explicitly instructed: "DO NOT implement anything and DO NOT change any other docs."
  • Sanitization: No validation or sanitization of input instructions or file content is performed.
  • [NO_CODE]: This skill consists entirely of natural language instructions and markdown templates. It does not contain any executable scripts (e.g., Python, JavaScript, Shell).
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 28, 2026, 06:32 AM