senior-developer
Pass
Audited by Gen Agent Trust Hub on Sep 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest task lists from a 'PM agent' and reference multiple external specification files (e.g.,
ai/system/component-library.md,ai/agents/dev.md). This architecture creates a surface where malicious instructions could be embedded in the data provided to the agent. - Ingestion points: Processes tasks from a project management agent and implementation methodology from
ai/agents/dev.md. - Boundary markers: The instructions do not define clear delimiters or 'ignore' directives to separate data from instructions during task processing.
- Capability inventory: As a developer agent, the skill assumes the capability to write and modify source code within the project environment.
- Sanitization: No explicit sanitization or validation logic is defined for the external task descriptions or documentation content.
Audit Metadata