hacker-news

Pass

Audited by Gen Agent Trust Hub on Jul 3, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill is a read-only data connector for public Hacker News information. No malicious code, obfuscation, or unauthorized data access patterns were identified.
  • [PROMPT_INJECTION]: The skill processes untrusted external data (Hacker News comments and stories) which presents an indirect prompt injection surface. This is a common characteristic of tools designed to read public web content.
  • Ingestion points: Data is ingested through operations such as hacker-news/items/{id} (fetching comment and story text) and hacker-news/stories/{feed}/items (fetching story titles).
  • Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded commands within the fetched data.
  • Capability inventory: The skill's operations are strictly read-only and it lacks high-risk capabilities such as file system writes, arbitrary command execution, or network exfiltration to third-party domains.
  • Sanitization: The instructions do not specify any sanitization or filtering of the fetched content.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 3, 2026, 04:06 PM
Security Audit — agent-trust-hub — hacker-news