iterate-design-discussion
Pass
Audited by Gen Agent Trust Hub on Oct 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external files located in the ".humanlayer/tasks/" directory (e.g., ticket.md, task.md, research documents). This ingestion surface could potentially be used to deliver malicious instructions embedded within legitimate-looking design artifacts.
- Ingestion points: External files within the ".humanlayer/tasks/" directory, as described in SKILL.md step 1.
- Boundary markers: The instructions do not specify the use of delimiters or safety wrappers when processing these files.
- Capability inventory: The skill has the ability to read, write, and edit files, as well as spawn sub-agents (codebase-locator, codebase-analyzer, etc.) to perform further actions, as detailed in SKILL.md steps 1, 3, and 4.
- Sanitization: There is no explicit sanitization or filtering logic mentioned for the content retrieved from external task files.
Audit Metadata