python-package-migrator
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze untrusted data from local project directories, creating an indirect prompt injection surface.
- Ingestion points: The skill accesses local project files (e.g.,
requirements.txt,pyproject.toml) via theproject_pathinput variable as documented inSKILL.mdandskill.yaml. - Boundary markers: Absent; there are no documented delimiters or instructions to the agent to ignore instructions embedded within the processed project files.
- Capability inventory: The skill references "Automated analysis of Python project structure" and "Integration with standard Python tooling," which implies the ability to execute environment-level commands.
- Sanitization: Absent; the documentation does not describe any validation or sanitization of the content extracted from project files.
- [NO_CODE]: The analyzed files (
SKILL.mdandskill.yaml) do not contain any executable scripts, shell commands, or logic. The skill currently acts as a descriptive manifest rather than a functional extension.
Audit Metadata