python-pro
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is intended for reviewing and writing Python codebases, which creates a surface for indirect prompt injection if the ingested code contains instructions designed to influence the agent.
- Ingestion points: Processes user-provided Python code and project configurations (
SKILL.md). - Boundary markers: No specific delimiters or "ignore instructions" markers are defined for handling external code content.
- Capability inventory: The skill enables the agent to interact with package managers, run performance profiles, and implement DevOps strategies, involving filesystem and shell access (
SKILL.md). - Sanitization: No explicit sanitization or validation logic is provided for external code strings.
- [DYNAMIC_EXECUTION]: The skill lists "Metaprogramming and dynamic code generation" as a capability under advanced Python patterns. While a legitimate advanced Python topic, it involves assembling and executing code at runtime.
Audit Metadata