skills/versusjl/devin-blueprint/plan/Gen Agent Trust Hub

plan

Pass

Audited by Gen Agent Trust Hub on Jul 2, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill facilitates standard project management workflows, such as task decomposition and plan generation, without engaging in suspicious behaviors like obfuscation, credential theft, or unauthorized network activity.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface because it processes untrusted data from user arguments, Linear tickets, and project specifications to generate its planning output.
  • Ingestion points: Found in SKILL.md, specifically using $ARGUMENTS, Linear tickets, and files within docs/ or charters/.
  • Boundary markers: The instructions lack explicit delimiters or instructions to prevent the agent from obeying commands embedded within the source data.
  • Capability inventory: The skill is authorized to read and write files (e.g., docs/<feature-slug>/plan.md) and potentially interact with the Linear API through agent tools.
  • Sanitization: There are no instructions for sanitizing or validating the content of the external inputs before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 2, 2026, 11:05 PM
Security Audit — agent-trust-hub — plan