ecosystem-security
Pass
Audited by Gen Agent Trust Hub on Apr 18, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill manifest defines a system for processing external data, which creates a vulnerability surface for indirect prompt injection attacks.\n
- Ingestion points: The skill is designed to ingest and analyze external
SKILL.mdfiles (via the security-auditor component) and incoming user messages (via the adaptive-guard component).\n - Boundary markers: No specific delimiters or "ignore previous instructions" warnings are documented to isolate potentially malicious commands embedded in audited or monitored data.\n
- Capability inventory: The system is instructed to perform static analysis, assign trust scores, and synthesize runtime guard rules based on its evaluation of the ingested content.\n
- Sanitization: There is no evidence of explicit sanitization, filtering, or validation logic for the external content processed by the system.
Audit Metadata