archive-thread

Pass

Audited by Gen Agent Trust Hub on Jul 27, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes git mv to relocate thread directories and mkdir -p to ensure the destination path exists. These are standard operations for the skill's purpose.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface (Category 8) by processing data from within the target thread directory. 1. Ingestion points: The agent reads file content and headers from the .pending-decisions/, .pending-reviews/, and .implementation-runs/ subfolders. 2. Boundary markers: No explicit delimiters or instructions to ignore nested commands are used when the agent processes the file content. 3. Capability inventory: The skill has the capability to perform file system moves (git mv) and directory creation (mkdir) based on its logic. 4. Sanitization: No validation or sanitization is performed on the data read from the repository files before it is summarized in the prompt context.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 27, 2026, 08:08 AM
Security Audit — agent-trust-hub — archive-thread