autopilot-predict

Pass

Audited by Gen Agent Trust Hub on Jun 13, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill identifies a potential surface for indirect prompt injection through its integration with historical pattern retrieval and autonomous execution logic.
  • Ingestion points: Data is ingested via mcp__claude-flow__autopilot_predict and mcp__claude-flow__autopilot_history as defined in SKILL.md.
  • Boundary markers: Absent; there are no instructions to the agent to treat retrieved history or predictions as untrusted or to use delimiters.
  • Capability inventory: The skill has the capability to execute tools directly based on predictions and breakdown tasks for prioritized execution (SKILL.md).
  • Sanitization: Absent; the instructions direct the agent to execute predictions immediately if a confidence threshold is met, without validation of the prediction content.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 13, 2026, 01:22 PM
Security Audit — agent-trust-hub — autopilot-predict