skills/konglong87/superpm/pm-abtest/Gen Agent Trust Hub

pm-abtest

Pass

Audited by Gen Agent Trust Hub on Aug 3, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill preamble executes a local update check script (check-update.sh) using the Bash tool. This is a maintenance operation targeting local files within the skill's environment and does not involve remote code execution.
  • [INDIRECT_PROMPT_INJECTION]: The skill features an indirect prompt injection surface. 1. Ingestion points: User input is collected via the AskUserQuestion tool in Steps 1 through 4. 2. Boundary markers: The skill employs a structured markdown template in Step 6 to organize the user input. 3. Capability inventory: The agent uses the Write tool for file creation and the Bash tool for the preamble. 4. Sanitization: No explicit escaping or filtering of user-provided strings is performed before they are written to the documentation files.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 3, 2026, 06:20 AM
Security Audit — agent-trust-hub — pm-abtest