tag-organize-cli

Pass

Audited by Gen Agent Trust Hub on May 22, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill interacts with the local system by executing the wpsnote-cli tool. It uses various subcommands such as stats, tags, read, and edit to manage note data.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes untrusted data from the user's notes.
  • Ingestion points: Note content is retrieved into the agent's context using the wpsnote-cli read and wpsnote-cli read-blocks commands in SKILL.md.
  • Boundary markers: There are no explicit delimiters or warnings to the AI model to ignore instructions embedded within the note content.
  • Capability inventory: The skill has the ability to modify or overwrite note content through the wpsnote-cli edit and wpsnote-cli batch-edit commands.
  • Sanitization: The skill does not implement sanitization or validation of the note content before it is processed by the AI model.
Audit Metadata
Risk Level
SAFE
Analyzed
May 22, 2026, 06:19 AM
Security Audit — agent-trust-hub — tag-organize-cli