create-implementation-plan
Pass
Audited by Gen Agent Trust Hub on Mar 21, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill uses authoritative directives intended to override standard AI reasoning and context-awareness, specifically requiring that instructions be interpreted literally and executed without human interpretation or clarification.
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by interpolating user-provided data into a template designed for machine-readability and autonomous execution.
- Ingestion points: The
${input:PlanPurpose}variable inSKILL.mdis directly included in the generated output. - Boundary markers: Absent; the template does not utilize delimiters or specific instructions to isolate the user input from the execution directives.
- Capability inventory: The skill writes persistent Markdown files to the
/plan/directory which are explicitly intended to drive further autonomous actions by AI agents. - Sanitization: No sanitization, validation, or filtering of the input content is performed to ensure the generated plans are free of malicious instructions.
Audit Metadata