aw-create-plan

Pass

Audited by Gen Agent Trust Hub on May 7, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a bash script to identify the current git branch and calculate the next version number for plan snapshots. It utilizes standard local utilities including git, mkdir, ls, sed, sort, and tail.
  • [PROMPT_INJECTION]: The skill ingests conversation context to populate a implementation plan template. While this creates an indirect prompt injection surface (where user-provided content is stored for later sessions), it is a core function of the skill's purpose and uses structured markdown templates as boundary markers.
  • [DATA_EXPOSURE]: The skill manages project documentation by writing to the local filesystem inside the .agent/ directory. No access to sensitive system files (e.g., SSH keys, credentials) or network exfiltration patterns were observed.
Audit Metadata
Risk Level
SAFE
Analyzed
May 7, 2026, 07:22 AM