devx-ux
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- Indirect Prompt Injection Surface: The skill directs the agent to evaluate local source code and documentation to provide UX feedback. While this is the intended purpose of the tool, it involves processing project data that could potentially contain embedded instructions.
- Ingestion points: The agent analyzes files such as
src/apm_cli/cli.py, help strings, and README documentation in the relative file pathSKILL.md. - Boundary markers: The instructions do not define specific delimiters or "ignore" directives to isolate project content from agent logic.
- Capability inventory: The skill's capabilities are focused on reviewing command-line interfaces, error messaging, and installation flows.
- Sanitization: No specific sanitization or validation of the ingested text is performed within this instruction set.
Audit Metadata