expert-advice

Pass

Audited by Gen Agent Trust Hub on Mar 27, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill includes a surface for prompt injection by directly interpolating user-provided text through the $ARGUMENTS variable at the end of the instruction block.
  • Ingestion points: User input is ingested via the $ARGUMENTS placeholder in SKILL.md.
  • Boundary markers: Absent. The user input is not enclosed in XML tags, triple backticks, or any other delimiters that would help the agent distinguish between instructions and data.
  • Capability inventory: The skill allows the agent to read the codebase ('Explore the current codebase') and perform network requests ('Fetch the Wasp docs').
  • Sanitization: Absent. There are no instructions to the agent to sanitize the input or ignore any command-like text within the user's request.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 27, 2026, 04:50 PM