skills/mtgvim/tiger-kit/tk-status/Gen Agent Trust Hub

tk-status

Pass

Audited by Gen Agent Trust Hub on Sep 11, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied session summaries and conversation history to generate a status card.
  • Ingestion points: Conversation context and user-provided summaries (SKILL.md).
  • Boundary markers: Output is constrained to a specific five-line text card format, and instructions mandate ending the turn immediately after presentation (SKILL.md).
  • Capability inventory: Read-only access to local Git state for repository/branch identification (SKILL.md).
  • Sanitization: The skill lacks explicit sanitization but contains strong instructions to never merge user goals or approvals and to use only established evidence.
  • [COMMAND_EXECUTION]: The skill performs a non-mutating read of the local environment to determine the current working context.
  • Evidence: Instructions allow a "cheap read of current Git state" if branch or repository identity is not already established (SKILL.md).
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 11, 2026, 01:52 AM
Security Audit — agent-trust-hub — tk-status