assigns

Pass

Audited by Gen Agent Trust Hub on Aug 6, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill features a surface for indirect prompt injection by interpolating user-provided data via the $ARGUMENTS placeholder directly into the instructions used to invoke another tool (phx:assigns-audit).\n
  • Ingestion point: User-provided arguments in SKILL.md.\n
  • Boundary markers: The skill does not use delimiters or boundary markers to isolate the untrusted user input from the rest of the instruction context.\n
  • Capability inventory: The skill triggers the execution of an external auditing tool/skill.\n
  • Sanitization: No sanitization, escaping, or validation is performed on the input before it is passed to the next tool.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 6, 2026, 01:40 AM
Security Audit — agent-trust-hub — assigns