launch-hacker-news

Pass

Audited by Gen Agent Trust Hub on Jul 16, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill provides instructions for installing companion skills from the vendor's official GitHub repository (github.com/ulpi-io/skills) if they are missing from the environment.
  • [COMMAND_EXECUTION]: Includes an environment-setup command (npx skills add) intended for agent or user execution to install additional dependencies.
  • [PROMPT_INJECTION]: The skill logic contains an indirect prompt injection surface as outlined in the evidence chain below:
  • Ingestion points: The skill uses a browsing tool to ingest data from external product websites and source repositories to inform launch strategy and positioning.
  • Boundary markers: The instructions do not define specific delimiters or directives for the agent to ignore or isolate embedded instructions within the fetched external data.
  • Capability inventory: The skill is authorized to write to the local filesystem (Write tool) and invoke logic from other installed skills (Skill tool).
  • Sanitization: No mechanisms for sanitizing, validating, or filtering the retrieved web content are described before the data is processed into prompt context.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 16, 2026, 10:13 AM
Security Audit — agent-trust-hub — launch-hacker-news