risk-register-manager
Pass
Audited by Gen Agent Trust Hub on Jul 27, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through the processing of external data files stored in the
./grc-data/risks/directory. - Ingestion points: The agent reads JSON and YAML files from the
./grc-data/risks/path to perform assessments and generate reports. - Boundary markers: There are no explicit instructions or delimiters defined to prevent the agent from obeying instructions embedded within the risk data files.
- Capability inventory: The skill utilizes 'Read', 'Write', and 'Glob' tools to interact with the file system.
- Sanitization: No sanitization or validation logic is specified to filter or escape potentially malicious natural language instructions within the risk descriptions or metadata fields.
Audit Metadata