moai-security-encryption
Pass
Audited by Gen Agent Trust Hub on Mar 1, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION]: The skill exposes an attack surface for indirect prompt injection by retrieving and processing external data within the agent's context.\n
- Ingestion points: External content is ingested via the
WebFetchtool and themcp__context7__get-library-docstool, which are used to retrieve cryptographic documentation and web data.\n - Boundary markers: The skill does not implement delimiters or specific instructions to isolate and ignore potentially malicious commands embedded in external content.\n
- Capability inventory: The agent is granted powerful tools including
Bash,Write,Edit,Glob, andGrep, which could be exploited if the agent obeys instructions from an external source.\n - Sanitization: There is no evidence of sanitization or validation of the fetched data before it is processed by the agent or incorporated into architectural designs.\n- [EXTERNAL_DOWNLOADS]: The skill references official cryptographic standards and reputable libraries (NIST, OWASP, RFCs, argon2, libsodium) for technical guidance and implementation templates.
Audit Metadata