proof

Pass

Audited by Gen Agent Trust Hub on Mar 2, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill fetches external markdown content from proofeditor.ai that is subsequently processed by the agent, creating a surface for indirect prompt injection.\n
  • Ingestion points: Document state and markdown content are retrieved via the WebFetch and Bash (curl) tools from https://www.proofeditor.ai/api/agent/{slug}/state.\n
  • Boundary markers: The instructions lack explicit delimiters or safety markers to differentiate between document content and agent instructions.\n
  • Capability inventory: The skill includes Bash and WebFetch permissions, which could be exploited by instructions embedded in a malicious document.\n
  • Sanitization: There is no evidence of sanitization, validation, or filtering of the content retrieved from the external API before it is presented to the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 2, 2026, 04:26 AM