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.md directs the agent to check https://fluxui.dev/docs/components/ for current API details when using components. This is a standard reference to official library documentation.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 29, 2026, 06:47 PM