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

linear-update

Pass

Audited by Gen Agent Trust Hub on Feb 28, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the linearis command-line interface to interact with the Linear platform for tasks such as updating issue status, priority, labels, and adding comments.\n- [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface by reading content from external Linear issues.\n
  • Ingestion points: External data is ingested via the linearis issues read command and saved to local files in /tmp/issue-ENG-1234.json.\n
  • Boundary markers: No delimiters or safety instructions are used to separate ingested external content from internal agent instructions.\n
  • Capability inventory: The skill has the ability to execute shell commands (linearis) and perform write operations to the file system and external API.\n
  • Sanitization: There is no evidence of sanitization, validation, or escaping of the issue content retrieved from the external source before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 28, 2026, 10:32 PM