famou-artifact-generator

Pass

Audited by Gen Agent Trust Hub on Jun 16, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill directs the agent to execute a generated Python script to verify task components during the implementation phase. Evidence: Step 7 explicitly instructs the agent to run the command python evaluator.py <path_to_init.py> to validate the functionality of the generated artifacts.
  • [PROMPT_INJECTION]: The workflow exhibits a surface for indirect prompt injection via the analysis of untrusted workspace files. * Ingestion points: Step 1 (Clarification Phase) requires the agent to read and understand existing project files, including data files, code scripts, READMEs, and configurations. * Capability inventory: The information extracted from these files directly influences the generation of problem.md and subsequent executable Python scripts (init.py, evaluator.py). * Boundary markers: The skill does not define explicit delimiters or instructions to ignore embedded commands within the analyzed project files. * Sanitization: There is no requirement for the agent to sanitize or validate the content of external files before incorporating their data into the prompt context or generated code.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 16, 2026, 10:15 AM
Security Audit — agent-trust-hub — famou-artifact-generator