skills/bholmesdev/skills/simplify/Gen Agent Trust Hub

simplify

Pass

Audited by Gen Agent Trust Hub on Mar 29, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is designed to ingest and modify code from the current workspace or user-provided state, which constitutes an indirect prompt injection surface. Maliciously crafted code or comments could attempt to influence the agent's behavior.
  • Ingestion points: Reviewing changes in the current branch or user-specified state in SKILL.md.
  • Boundary markers: Absent; there are no instructions to the agent to disregard instructions embedded within the code being simplified.
  • Capability inventory: The agent is given instructions to modify and refine existing code, providing a mechanism for potential unauthorized code changes if triggered by injection.
  • Sanitization: Absent; the skill does not specify any validation or sanitization of the input code before the simplification process is applied.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 29, 2026, 06:56 PM