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 --jsoncommand, 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, andSlashCommandtools, 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