four-risks-check
Pass
Audited by Gen Agent Trust Hub on Nov 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection by reading and updating existing risk assessment documents from the project environment during its UPDATE mode.
- Ingestion points: Reads content from files located within the
product/,discovery/,risks/, andplanning/directories. - Boundary markers: Absent. The skill does not implement specific delimiters or instructions to ignore or isolate potentially malicious instructions embedded within the files it processes.
- Capability inventory: The skill utilizes file search and read operations to retrieve existing assessments and file write operations to save updated markdown files.
- Sanitization: Absent. There is no evidence of content validation or sanitization for the data retrieved from local project files before it is processed by the agent.
Audit Metadata