skills/eveld/claude/linear-awareness/Gen Agent Trust Hub

linear-awareness

Pass

Audited by Gen Agent Trust Hub on Feb 28, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill establishes an indirect prompt injection surface by instructing the agent to extract and analyze technical data from Linear tickets. 1. Ingestion points: External ticket descriptions and technical comments processed via the linear-analyzer tool. 2. Boundary markers: The instructions lack specific delimiters to isolate external ticket content from the prompt context. 3. Capability inventory: The skill set includes write access to the ticket system and the ability to execute linearis CLI commands. 4. Sanitization: No sanitization or validation of the ingested ticket content is mentioned.
  • [COMMAND_EXECUTION]: The skill guidelines facilitate direct interaction with the system shell by recommending the use of the linearis CLI for creating issues and managing projects or users.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 28, 2026, 10:32 PM