NYC

developer-growth-analysis

Pass

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: LOWNO_CODE
Full Analysis
  • [NO_CODE] (LOW): The submission only includes the metadata.json file. The referenced logic and instructions in SKILL.md are absent, preventing an evaluation of command execution, data handling, or potential obfuscation.\n- [DATA_EXFILTRATION] (INFO): The metadata description indicates that the skill is designed to read private Claude Code chat history and transmit data to Slack. This specific capability (sensitive read + network write) constitutes a high-risk surface for data exfiltration that must be verified against the missing implementation.\n- [PROMPT_INJECTION] (INFO): According to the metadata, the skill ingests content from HackerNews. This ingestion of external, untrusted data creates a vulnerability surface for indirect prompt injection, which can only be assessed by reviewing the prompt delimiters and sanitization logic in the primary skill file.
Audit Metadata
Risk Level
LOW
Analyzed
Feb 16, 2026, 11:12 AM