cross-reference-linking

Pass

Audited by Gen Agent Trust Hub on Sep 22, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE]: The skill consists entirely of markdown instructions, parameters, and evaluation examples. There are no scripts, binaries, or automated tasks associated with this skill.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process user-provided finding summaries which represents an ingestion surface for potentially untrusted data.
  • Ingestion points: The finding_summary parameter defined in SKILL.md accepts free-form text input.
  • Boundary markers: No explicit delimitation or instructions to ignore embedded commands are present in the skill markdown.
  • Capability inventory: The skill provides no executable code, file-system access, or network tools that could be abused via injection.
  • Sanitization: No validation or sanitization routines are defined for the input parameters.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 22, 2026, 07:56 AM