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 WebFetch tool and the mcp__context7__get-library-docs tool, 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, and Grep, 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
Risk Level
SAFE
Analyzed
Mar 1, 2026, 01:07 AM