skills/open-gsd/gsd-core/gsd-next/Gen Agent Trust Hub

gsd-next

Pass

Audited by Gen Agent Trust Hub on Jul 11, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection by ingesting and acting upon local project and workflow state.\n
  • Ingestion points: The skill reads project state using the gsd-tools smart-entry --json command, which processes content from the local file system and environment.\n
  • Boundary markers: No explicit boundary markers or instructions to disregard instructions embedded in the project state are provided in the skill instructions.\n
  • Capability inventory: The skill is authorized to use Bash, Read, Glob, and SlashCommand tools, which could be misused if the routing logic is compromised by malicious project metadata.\n
  • Sanitization: There is no evidence of sanitization or strict schema validation performed on the JSON output retrieved from the project detection tool before it influences the agent's behavior.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 11, 2026, 09:38 PM
Security Audit — agent-trust-hub — gsd-next