claude-certification
Pass
Audited by Gen Agent Trust Hub on Oct 30, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches educational content, including lesson markdown, JSON-based track definitions, and Python scripts from the author's repository at
github.com/rohitg00/ai-engineering-from-scratch. This is a core function for retrieving the latest certification materials. - [COMMAND_EXECUTION]: To verify practical labs, the skill executes Python scripts (
main.py) and runs unit tests using thepython3interpreter. This capability is required for the interactive learning and scoring features described in the instructions. - [INDIRECT_PROMPT_INJECTION]: The skill processes external data (lesson docs, quizzes) fetched from a remote repository, which represents an attack surface for indirect prompt injection if the source repository were to be compromised.
- Ingestion points: Reads files from
raw.githubusercontent.com/rohitg00/ai-engineering-from-scratch/main/and local clones. - Boundary markers: None explicitly defined for external content.
- Capability inventory: File system writes (state management), network read access, and local command execution (
python3). - Sanitization: No specific sanitization or filtering of the fetched content is documented before it is processed by the agent.
Audit Metadata