tdd
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill implements a multi-agent pipeline where output from one agent is used as input for the next, creating a vulnerability surface for indirect prompt injection.
- Ingestion points: The prompts for Phases 2, 3, and 4 in SKILL.md ingest untrusted data from previous stages.
- Boundary markers: Absent; no delimiters or ignore-instructions are used for interpolated data.
- Capability inventory: The agents have the ability to write production code and execute shell commands via npm and pytest.
- Sanitization: Absent; no escaping or validation of inputs is performed between workflow stages.
Audit Metadata