iterate-tech-design
Pass
Audited by Gen Agent Trust Hub on Oct 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources, creating a potential surface for indirect prompt injection.
- Ingestion points: The agent reads all files within the
.humanlayer/tasks/directory, includingticket.md,task.md, design discussions, and external research artifacts. - Boundary markers: There are no explicit instructions for using delimiters or "ignore embedded instructions" warnings when processing these files.
- Capability inventory: The agent has the ability to modify files using the
Edittool and spawn additionalAgent()calls for codebase research. - Sanitization: The skill does not mention sanitizing or escaping the content retrieved from external task files before incorporating it into the design process.
Audit Metadata