feature-presentation

Pass

Audited by Gen Agent Trust Hub on Nov 4, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill invokes several internal Node.js scripts to perform validation and export operations.
  • Evidence: Executes .claude/scripts/set-active-plan.cjs to manage session state.
  • Evidence: Executes .claude/skills/presentation-builder/scripts/validate-presentation.cjs to ensure the generated HTML meets project standards.
  • Evidence: Executes .claude/skills/html-export/scripts/export.cjs to generate PDF or PNG versions of the slides.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes content from various project files which could contain embedded instructions intended to influence the agent or the generated output.
  • Ingestion points: Reads artifact files from team-artifacts/ (initiatives, tasks, user stories, design-specs) and Feature Specs from docs/specs/ (SKILL.md Step 1).
  • Boundary markers: The skill does not define specific delimiters for separating ingested content from system instructions, relying instead on its parsing logic.
  • Capability inventory: The skill can write files to the local filesystem and execute defined internal Node.js tools.
  • Sanitization: The skill implements a robust defense against injection within the generated HTML. references/deck-template.md mandates HTML escaping of all inserted values (using the correct &-first replacement order) and provides a specific four-step escaping protocol for content embedded in iframe srcdoc attributes to prevent cross-site scripting (XSS) and DOM breakouts.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 4, 2026, 10:12 AM