quality-manager-qmr
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill employs Python scripts, namely
management_review_tracker.pyandquality_effectiveness_monitor.py, which are designed to ingest data from external JSON and CSV sources. The agent consumes the resulting reports, creating a surface where data-embedded instructions could influence agent behavior.\n - Ingestion points: External data enters the skill's context through scripts reading local files via
--dataand--metricsarguments.\n - Boundary markers: The skill lacks explicit delimiters or instructions to the agent to treat external data as untrusted or to ignore instructions found within the data.\n
- Capability inventory: Scripts perform data parsing and statistical reporting; they do not have capabilities for network communication, privileged file access, or system modification.\n
- Sanitization: No sanitization is performed on text-based data fields before they are interpolated into the final reports presented to the agent.
Audit Metadata