mining-maintenance
Pass
Audited by Gen Agent Trust Hub on Mar 23, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes untrusted data from the project environment (e.g., fleet management records, CMMS data, and maintenance history) without explicit boundary markers or sanitization. An attacker who can modify these data files could potentially influence the agent's analysis or output.
- Ingestion points: Phase 1 (Fleet Discovery) and Phase 2 (Condition Monitoring) instructions to read project-based fleet management data and maintenance systems (SAP PM, Maximo, etc.).
- Boundary markers: None identified. The external data is interpolated directly into the agent's context.
- Capability inventory: File reading (project data) and file writing (generating reports in
docs/and telemetry in~/.claude/). - Sanitization: No sanitization or validation of the ingested data is performed before processing.
- [PROMPT_INJECTION]: The skill uses the
$ARGUMENTSvariable to define the analysis target. If a user provides malicious instructions within these arguments, it could lead to direct prompt injection, potentially overriding the skill's intended behavior.
Audit Metadata