technician-productivity

Pass

Audited by Gen Agent Trust Hub on Mar 23, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it processes untrusted data from the codebase and external data models without boundary markers.
  • Ingestion points: Reads technician time tracking, job completion records, KPI configurations, and organizational data in Phases 1 through 5.
  • Boundary markers: Absent; there are no delimiters or specific instructions for the agent to ignore instructions embedded within the analyzed data.
  • Capability inventory: The skill writes reports to the local file system (docs/) and appends telemetry metadata to ~/.claude/projects/.
  • Sanitization: Absent; the skill does not explicitly validate or filter content ingested from the project files.
  • [DATA_EXPOSURE]: The skill accesses sensitive operational data including technician IDs, GPS-based time tracking, revenue, and job costs. This access is consistent with its stated purpose of field service productivity analysis.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 23, 2026, 10:57 AM
Security Audit — agent-trust-hub — technician-productivity