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_predictandmcp__claude-flow__autopilot_historyas 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