gsd-resume-work
Pass
Audited by Gen Agent Trust Hub on Mar 12, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill restores session context by reading local project files, which creates an indirect prompt injection surface.
- Ingestion points: STATE.md, CONTEXT.md, and checkpoint files (.continue-here).
- Boundary markers: No delimiters or instructions to ignore embedded commands are defined.
- Capability inventory: The skill has access to Bash, Read, and Write tools.
- Sanitization: No content validation or sanitization is performed on the ingested data.
Audit Metadata