skills/nsantini/gsdl/gsdl-create-plan/Gen Agent Trust Hub

gsdl-create-plan

Pass

Audited by Gen Agent Trust Hub on Mar 22, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from Product Requirement Documents (PRD) to generate implementation plans. While this represents a surface for indirect prompt injection, the risk is mitigated by the skill's specific output format and a mandatory user confirmation phase.
  • Ingestion points: Reads PRD files from the .planning/[project-name]/tasks/ directory.
  • Boundary markers: Absent; the skill does not explicitly use delimiters to separate instructions from PRD content during analysis.
  • Capability inventory: The skill possesses file-writing capabilities to save generated task lists to the local disk.
  • Sanitization: No explicit sanitization or filtering of the ingested PRD content is described.
  • [COMMAND_EXECUTION]: The skill instructions include a reference to npx jest within the output template for the generated markdown file. This is provided as instructional text for the developer implementing the plan and does not constitute a command execution request for the agent itself.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 22, 2026, 10:16 PM
Security Audit — agent-trust-hub — gsdl-create-plan