skills/rsmdt/the-startup/refactor/Gen Agent Trust Hub

refactor

Pass

Audited by Gen Agent Trust Hub on Mar 4, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it reads and processes untrusted code. Maliciously crafted comments or strings within that code could contain instructions designed to manipulate the analysis subagents.
  • Ingestion points: Source code files are read using Read, Grep, and Glob tools as specified in SKILL.md.
  • Boundary markers: Absent; the system does not use specific delimiters or instructions to ignore embedded instructions in the source data.
  • Capability inventory: The skill has access to Bash, Edit, Write, MultiEdit, and Task tools for execution and orchestration as defined in SKILL.md.
  • Sanitization: Safety is managed through strict constraints on behavior preservation and mandatory test verification steps.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 4, 2026, 11:27 AM