skills/amit-t/skills/design-draft/Gen Agent Trust Hub

design-draft

Pass

Audited by Gen Agent Trust Hub on Oct 31, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill reads Project Requirements Documents (PRDs) from an external directory (../refinery-pm-os/outputs/prds/approved/) to drive its multi-step workflow. These files are processed to generate code and documentation, creating a surface for indirect prompt injection where malicious content in a PRD could influence the agent's behavior.
  • Ingestion points: Reads markdown files from ../refinery-pm-os/outputs/prds/approved/ and context-library/prds/ (SKILL.md, Step 0 and 1).
  • Boundary markers: None specified for the external data ingestion.
  • Capability inventory: The skill can write files to multiple outputs/ subdirectories and execute a shell script (./scripts/uxd-approve.zsh).
  • Sanitization: No sanitization or validation of the PRD content is described before use in prompts.
  • [DYNAMIC_EXECUTION]: The skill dynamically generates and modifies executable code at runtime.
  • Evidence: Step 6 generates HTML files in outputs/screens/ with embedded JavaScript onclick handlers for navigation. Step 8b instructs the agent to programmatically update outputs/screens/manifest.js with new data structures.
  • [COMMAND_EXECUTION]: The skill executes a local shell script to finalize the workflow.
  • Evidence: Step 9 executes ./scripts/uxd-approve.zsh [FEATURE-ID]. The FEATURE-ID is derived from external file names or user input.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 31, 2026, 04:28 PM