Skills
Navigate
skills/pixazo-ai/skills/magi/Gen Agent Trust Hub

magi

Pass

Audited by Gen Agent Trust Hub on Sep 22, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted input from the user and external data from vendor endpoints, creating a potential surface for indirect prompt injection.\n
  • Ingestion points: User prompt parameters and API documentation from https://www.pixazo.ai/models/magi.md as described in SKILL.md.\n
  • Boundary markers: No specific delimiters or instructions to ignore embedded commands are present in the data processing flow.\n
  • Capability inventory: The skill utilizes network communication (Python requests, Node fetch) and shell command execution (curl) within SKILL.md.\n
  • Sanitization: There is no evidence of sanitization or validation of external content before it is processed by the agent.\n- [COMMAND_EXECUTION]: SKILL.md contains instructions for using the curl tool to interact with the API.\n- [EXTERNAL_DOWNLOADS]: The skill references and fetches documentation from www.pixazo.ai, which is the vendor's official domain.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 22, 2026, 09:02 PM