skills/decisionnerd/dev-skills/kiss/Gen Agent Trust Hub

kiss

Pass

Audited by Gen Agent Trust Hub on Oct 23, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external data such as repository documentation, source code, and user-provided text. This processing of untrusted data represents an attack surface for indirect prompt injection.\n
  • Ingestion points: Workflow instructions in SKILL.md specify reading docs, code, issue graphs, and user pastes.\n
  • Boundary markers: There are no explicit instructions to use delimiters or ignore embedded commands within the analyzed data.\n
  • Capability inventory: The skill is configured to perform read operations and can orchestrate subagents via platform tools (e.g., Claude Code's Workflow tool).\n
  • Sanitization: The instructions do not define specific sanitization or escaping mechanisms for the external data it processes.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 23, 2026, 01:31 AM