pdca-watch
Pass
Audited by Gen Agent Trust Hub on Aug 31, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from local JSON and NDJSON files (
pdca-status.json,token-ledger.ndjson) to display a progress dashboard. - Ingestion points: Files located in
.bkit/state/and.bkit/runtime/as defined inSKILL.md. - Boundary markers: None explicitly defined in the instructions for the rendered output.
- Capability inventory: The skill uses the
ReadandGlobtools and executes local logic fromlib/dashboard/watch.js. It lacks network or write capabilities. - Sanitization: The skill documentation notes that PII redaction is managed by the data source provider.
- [DATA_EXPOSURE_AND_EXFILTRATION]: The skill reads project-specific state files (
pdca-status.jsonandtoken-ledger.ndjson). This access is local and intended for the dashboard functionality. No exfiltration patterns (network tools, external URLs) or access to standard sensitive credentials (e.g., SSH keys, AWS configs) were found.
Audit Metadata