survey-data-processor
Pass
Audited by Gen Agent Trust Hub on Aug 26, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill is designed to process external survey data (point clouds, total station measurements, and GNSS data) and grants the agent file manipulation and shell access capabilities. This creates a potential attack surface for indirect prompt injection where malicious instructions embedded in data files could influence agent behavior.
- Ingestion points: The
SKILL.mdfile identifies several external data types for processing, includingpoint-cloud,total-station, andGNSSdata. - Boundary markers: The instructions do not define any specific delimiters or warnings to ensure the agent distinguishes between data content and operational instructions.
- Capability inventory: The skill allows access to
Bash,Write, andEdittools, which provide significant system interaction capabilities should an injection occur. - Sanitization: The provided documentation does not specify any validation or sanitization routines for the ingested data.
- [NO_CODE]: The skill consists primarily of markdown documentation and YAML configuration. It does not include any accompanying scripts, executables, or complex logic, which significantly limits the potential for direct malicious behavior within the skill itself.
Audit Metadata