mcpa-certification
Pass
Audited by Gen Agent Trust Hub on Oct 30, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses
python3to run practical labs (main.py) and execute unit tests (unittest) found within the repository structure. - [DYNAMIC_EXECUTION]: Script execution is dynamic, as the agent is instructed to locate and run Python files based on paths defined in external configuration files like
mcpa-f.json. - [EXTERNAL_DOWNLOADS]: The skill fetches certification program data, lesson Markdown, quizzes, and scripts from the
rohitg00/ai-engineering-from-scratchrepository on GitHub when a local clone is unavailable. - [INDIRECT_PROMPT_INJECTION]: The skill presents an attack surface for indirect prompt injection due to its ingestion of external content.
- Ingestion points: Reads data from
program.json,mcpa-f.json, lesson Markdown files (en.md), andquiz.json(found inSKILL.md). - Boundary markers: The instructions do not define explicit boundary markers or warnings for the agent to ignore instructions embedded within the curriculum data.
- Capability inventory: The skill has the capability to execute shell commands via
python3(found inSKILL.md). - Sanitization: There is no evidence of sanitization or filtering applied to the fetched educational content before it is processed by the agent.
Audit Metadata