skills/voska/hn-cli/hn/Gen Agent Trust Hub

hn

Pass

Audited by Gen Agent Trust Hub on Aug 26, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires the installation of an external binary via go install github.com/voska/hn-cli/cmd/hn@latest. This introduces a dependency on a tool hosted on a public repository.
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface because it ingests untrusted third-party content (Hacker News posts and comments).
  • Ingestion points: Untrusted content enters the agent's context through the hn search, hn front, and hn read commands.
  • Boundary markers: No delimiters or isolation instructions are present in SKILL.md to help the agent distinguish between tool output and potential malicious instructions within that output.
  • Capability inventory: The skill is a reader that puts data into the context; while it doesn't specify dangerous file-system or network write tools, the data can influence how the agent uses other capabilities in its environment.
  • Sanitization: No sanitization or filtering is performed on the data retrieved from the Hacker News API.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 26, 2026, 03:47 AM
Security Audit — agent-trust-hub — hn