lean-task
Pass
Audited by Gen Agent Trust Hub on Nov 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and act upon data from the project environment (such as source code and instructions), which establishes a vulnerability surface for indirect prompt injection.\n
- Ingestion points: The skill instructs the agent to "Read applicable project instructions and only task-relevant context" from the project environment.\n
- Boundary markers: No specific delimiters or instructions are provided to the agent to help it ignore or isolate instructions found within the processed project files.\n
- Capability inventory: The skill grants the agent the authority to modify application files (implementation) and execute commands (testing and validation).\n
- Sanitization: There are no instructions for the agent to sanitize, validate, or filter the content ingested from the external project context before acting upon it.
Audit Metadata