abstract-automation

Pass

Audited by Gen Agent Trust Hub on Mar 28, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill creates an attack surface for indirect prompt injection by instructing the agent to fetch and act upon data from the external Abstract design platform.\n
  • Ingestion points: Untrusted data enters the agent's context through tools like RUBE_SEARCH_TOOLS and other Abstract-specific operations used to retrieve project data, comments, and schemas as described in SKILL.md.\n
  • Boundary markers: The instructions do not specify any delimiters or safety warnings to help the agent distinguish between its instructions and the data fetched from the external platform.\n
  • Capability inventory: The skill utilizes powerful capabilities including RUBE_MULTI_EXECUTE_TOOL for multi-step execution and RUBE_REMOTE_WORKBENCH for potentially broad operations across files and remote environments.\n
  • Sanitization: The instructions do not include steps for sanitizing, validating, or escaping data retrieved from the Abstract API before it is used to influence the agent's next actions.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 28, 2026, 05:46 PM