verify-sources

Pass

Audited by Gen Agent Trust Hub on Apr 4, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection in its track verification process.
  • Ingestion points: The agent ingests potentially untrusted content from RESEARCH.md, SOURCES.md, and various track files via the Read tool.
  • Boundary markers: The instructions do not define delimiters or markers to isolate the ingested file content from the agent instructions.
  • Capability inventory: The skill has access to Edit, Bash, and the bitwize-music-mcp tool, representing a significant capability set if an injection occurred.
  • Sanitization: There is no evidence of validation or sanitization of the data read from external files before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 4, 2026, 10:06 PM