bulk-complete

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION] (SAFE): The skill executes a local Python script (scripts/bulk-complete.py) to automate task completion. The command parameters are structured and do not indicate shell injection or arbitrary code execution risks.- [DATA_EXPOSURE] (SAFE): The skill accesses and modifies project-specific files (steps.md, tasks.md). It does not appear to access sensitive system directories, credentials, or exfiltrate data to external servers.- [INDIRECT_PROMPT_INJECTION] (LOW): The skill reads from and writes to user-controlled markdown files. While this creates a surface for indirect prompt injection, the specific functionality (marking tasks as complete) is narrow and unlikely to lead to agent takeover without more complex interactions.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:13 PM