prepare-walkthrough-presentation
Pass
Audited by Gen Agent Trust Hub on Oct 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external markdown data from a codebase walkthrough, which represents a potential surface for indirect prompt injection.\n
- Ingestion points: The skill reads multiple artifacts from the walkthrough directory, including unified-walkthrough.md, sections/.md, validation-report-.md, coverage-plan.md, entry-points.md, and open-questions.md (SKILL.md).\n
- Boundary markers: No specific delimiters or safety instructions are defined to encapsulate the ingested content or prevent sub-agents from executing instructions potentially hidden within the source documents.\n
- Capability inventory: The skill is limited to reading local walkthrough files and writing markdown deck outlines to the presentation/ subdirectory. It does not utilize network tools, system command execution, or other high-risk capabilities.\n
- Sanitization: There is no evidence of content sanitization or validation of the input artifacts before they are passed to the sub-agents for processing.
Audit Metadata