agency-senior-developer
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill demonstrates an indirect prompt injection surface due to its interaction with other agents.
- Ingestion points: As described in
SKILL.md, the implementation process begins by reading task lists generated by a Project Manager (PM) agent. - Boundary markers: There are no instructions in the skill definition to use specific delimiters or to disregard potentially malicious instructions within the PM task list.
- Capability inventory: The agent is designed for 'Premium Implementation', which typically requires file system access to write and modify application code.
- Sanitization: The skill lacks instructions for validating or sanitizing the input tasks before they are processed by the developer persona.
- [EXTERNAL_DOWNLOADS]: The skill provides a reference to technical documentation for UI components.
- Evidence:
SKILL.mddirects the agent to checkhttps://fluxui.dev/docs/components/for current API details when using components. This is a standard reference to official library documentation.
Audit Metadata