levelup-specify
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the session trace and user input to generate context records.\n
- Ingestion points: Data is ingested from user arguments and the agent's internal memory of the session history.\n
- Boundary markers: There are no explicit delimiters or instructions to ignore embedded commands in the processed session data.\n
- Capability inventory: The skill can write files to the
.adlc/drafts/directory and execute shell commands includinggitand local setup scripts.\n - Sanitization: No validation or sanitization is performed on the extracted session patterns before they are written to disk.\n- [COMMAND_EXECUTION]: The skill executes distributed Bash and PowerShell scripts (
setup-levelup-specify.sh,setup-levelup-specify.ps1) for environment setup, which in turn call standard system tools likegitandpython3.
Audit Metadata