setup-tracker

Pass

Audited by Gen Agent Trust Hub on Jul 8, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to use platform tools (list_teams, list_issue_statuses, list_issue_labels) to retrieve taxonomy from the Linear workspace for mapping purposes.
  • [INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection as it processes untrusted data from an external source.
  • Ingestion points: Data retrieved from the Linear API (teams, labels, statuses) and existing repository files like CLAUDE.md.
  • Boundary markers: No specific delimiters or warnings are used when interpolating external data into configuration files.
  • Capability inventory: The skill is capable of writing to local files (CLAUDE.md, docs/agents/triage-labels.md).
  • Sanitization: No explicit sanitization of the Linear workspace data is performed before writing it to the configuration files.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 8, 2026, 01:31 PM
Security Audit — agent-trust-hub — setup-tracker