skills/filipas123/kimi-atlas/atlas/Gen Agent Trust Hub

atlas

Pass

Audited by Gen Agent Trust Hub on Nov 22, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted data from multiple sources, creating a potential surface for indirect prompt injection attacks.
  • Ingestion points: Processes user-provided arguments, file contents via the Read tool, results from WebSearch, and content retrieved via FetchURL (SKILL.md).
  • Boundary markers: Implements a 'SAFE-2' rule that explicitly instructs the agent to treat all ingested content as data to be summarized, rather than instructions to be followed (SKILL.md).
  • Capability inventory: The skill possesses significant capabilities, including the ability to Write and Edit files, execute shell commands via Bash, and dispatch subagents through the Agent tool (SKILL.md).
  • Sanitization: Uses 'untrusted-content framing' when passing data to subagents, though it primarily relies on the model's adherence to the 'SAFE-2' instructions (SKILL.md).
  • [DYNAMIC_EXECUTION]: The orchestrator's core logic is implemented through Python scripts executed dynamically via shell heredocs.
  • Evidence: The skill uses `python3
  • <<'PY' ... PYandpython3 -c` to perform state management, argument parsing, and verification tasks (SKILL.md).
  • Mitigation: The skill enforces the use of PYTHONSAFEPATH=1 and explicitly checks for this flag to prevent module shadowing attacks where a target repository could provide malicious versions of the skill's own dependencies (SKILL.md).
  • [COMMAND_EXECUTION]: The skill makes extensive use of the Bash tool to orchestrate its workflow.
  • Evidence: Uses shell commands to manage directories, perform git operations (like creating isolated worktrees), and invoke its own Python-based verification harness (SKILL.md).
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 22, 2026, 01:12 AM