genkit-prompts-python
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to audit and build Genkit Dotprompt templates and implementation code provided by the user, which creates a surface for indirect prompt injection attacks.
- Ingestion points: The skill processes user-supplied
.promptfiles, generate calls, and Genkit code snippets as described in the 'Audit workflow' and 'Build workflow' sections (SKILL.md). - Boundary markers: There are no explicit delimiters or specific instructions for the agent to ignore potentially malicious embedded commands within the audited data.
- Capability inventory: The skill is configured to use specialized tools for searching and reading documentation (
search_genkit_docs,read_genkit_docs). - Sanitization: The skill does not mention any sanitization or validation logic to filter out harmful instructions from the input data before processing it.
Audit Metadata