skills/jonaskahn/specwright/sw-shape/Gen Agent Trust Hub

sw-shape

Pass

Audited by Gen Agent Trust Hub on Nov 11, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted external data such as user-pasted proposals, snapshots, and attachments. It includes proactive defensive instructions for the agent to treat this content strictly as data, avoid executing embedded commands, and flag any suspected prompt injection attempts to the user.
  • [DYNAMIC_EXECUTION]: The included Python scripts (leakage.py and new_epic.py) dynamically modify the Python system path to load internal library components (kitlib) from a shared local directory. This is a standard pattern for modularity within the vendor's toolset and does not involve untrusted code sources.
  • [COMMAND_EXECUTION]: The skill's procedure involves executing specific local Python scripts to automate design-leakage checks and identifier reservations. These executions are restricted to scripts shipped with the skill and are performed as part of its primary functional purpose.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 11, 2026, 08:31 AM