ln-230-story-prioritizer

Pass

Audited by Gen Agent Trust Hub on Apr 25, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches shared reference files and documentation from the author's official GitHub repository when they are not present in the local environment.\n- [PROMPT_INJECTION]: The skill processes untrusted story data from external sources, which could lead to indirect prompt injection if the data contains malicious instructions.\n
  • Ingestion points: Story titles, descriptions, and metadata fetched from Linear, GitHub, or local markdown files.\n
  • Boundary markers: No specific delimiters or safety instructions are defined to separate ingested story content from the agent's internal logic.\n
  • Capability inventory: The skill uses WebSearch and mcp__Ref tools and has the ability to write files to the local filesystem.\n
  • Sanitization: No input validation or content filtering is performed on the stories before they are used to build research queries.\n- [COMMAND_EXECUTION]: Executes shell commands such as 'mkdir' to create output paths and 'gh' to interact with GitHub issues and sub-issues.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 25, 2026, 07:29 PM