status
Pass
Audited by Gen Agent Trust Hub on Feb 19, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION] (SAFE): The skill executes various local CLI commands (
git,ao,bd,gt) to aggregate status data. These operations are used for information gathering and do not perform destructive actions or modifications to the system. - [DATA_EXPOSURE] (SAFE): The skill reads metadata and state files from the
.agents/directory (e.g.,chain.jsonl,sessions/,learnings/). This data is processed locally to generate the dashboard and is not transmitted externally. - [INDIRECT_PROMPT_INJECTION] (LOW):
- Ingestion points: Untrusted data enters the agent context through
gt mail inbox(external messages) andbd list(project issue titles). - Boundary markers: Absent. Tool outputs are interpolated directly into the dashboard display template.
- Capability inventory: The skill's scripts are restricted to read-only status commands; no file-writing or network-outward capabilities were detected across the analyzed scripts.
- Sanitization: None. External content is rendered without escaping, though the impact is negligible as the agent only uses this for display and internal state suggestions.
Audit Metadata