context-restore
Pass
Audited by Gen Agent Trust Hub on Nov 16, 2026
Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: Executes several specialized binaries located in
~/.claude/skills/gstack/bin/(includinggstack-skill-start,gstack-slug,gstack-paths, andgstack-skill-end) for state management and telemetry tasks. - [DATA_EXFILTRATION]: Transmits telemetry and operational data (such as session status, outcome, and insights) to the vendor's platform using the
gstack-skill-endandgstack-learnings-logutilities. - [INDIRECT_PROMPT_INJECTION]: The skill processes session transcripts (
.jsonl) and checkpoint files (.md), which are potential sources of indirect prompt injection. - Ingestion points: Reads files from
~/.claude/projects/and project-specific checkpoints directories. - Boundary markers: Contains explicit instructions to treat transcript contents as data rather than instructions and to flag any text attempting to command the agent.
- Capability inventory: Employs shell execution via
Bashand user interaction throughAskUserQuestion. - Sanitization: References the use of
gstack-redactto ensure data is cleaned before being quoted or used externally.
Audit Metadata