skills/nsantini/gsdl/gsdl-decompose/Gen Agent Trust Hub

gsdl-decompose

Pass

Audited by Gen Agent Trust Hub on Aug 11, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its handling of untrusted project data.
  • Ingestion points: Reads functional requirements and user stories from .planning/[project-name]/SPEC.md and project metadata from .planning/[project-name]/seed.md.
  • Boundary markers: No explicit delimiters or instructions to ignore embedded commands within the SPEC.md file are provided to the agent.
  • Capability inventory: The skill writes task lists to .planning/[project-name]/tasks.md and delegates external tracker modifications to a subagent running gsdl-tracker-sync.
  • Sanitization: The instructions do not define sanitization or validation logic for the content ingested from the project specification files.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 11, 2026, 08:13 AM
Security Audit — agent-trust-hub — gsdl-decompose