yc-weekly-growth-compass
Pass
Audited by Gen Agent Trust Hub on Sep 2, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill instructions and metadata are consistent with its stated purpose of providing a growth metrics calculator. No obfuscation, prompt injection, or persistence mechanisms were found.
- [COMMAND_EXECUTION]: The skill uses the terminal toolset to execute a local script
scripts/growth-compass.py. Analysis of the script confirms it is restricted to mathematical operations and standard output. It does not perform any network requests, sensitive file access, or administrative actions. - [REMOTE_CODE_EXECUTION]: The skill specifies 'zero external dependencies' and only uses the Python standard library (
math,json,sys,argparse). There are no patterns involving the download or execution of remote code. - [INDIRECT_PROMPT_INJECTION]: While the skill ingests user metrics, the data is processed by a Python script that strictly parses inputs as floating-point numbers. This structure prevents malicious strings from being interpreted as instructions by the agent.
Audit Metadata