momentum-planner
Pass
Audited by Gen Agent Trust Hub on Aug 20, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes data from external sources.
- Ingestion points: Ingests shipping roadmaps, analytics exports, and community telemetry from Hacker News and GDELT.
- Boundary markers: The instructions explicitly mandate treating exports and threads as untrusted input and ignoring embedded instructions.
- Capability inventory: The skill can write results to memory directories and propose event data via the registry-events.py script.
- Sanitization: The skill relies on instructional guardrails for the agent to ignore malicious commands instead of technical sanitization.
Audit Metadata