Skills
skills/pawpair/paw-mail-cli/paw-mail-usage/Gen Agent Trust Hub

paw-mail-usage

Pass

Audited by Gen Agent Trust Hub on Mar 1, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Provides instructions to install the paw-mail CLI from the author's repository (github.com/pawpair/paw-mail-cli).
  • [COMMAND_EXECUTION]: Requests permissions to execute paw-mail and paw-mail-tui binaries as defined in SKILL.md. It also includes commands for manual installation using system package managers, such as sudo dpkg.
  • [PROMPT_INJECTION]: Enables the agent to read email content, which serves as a surface for indirect prompt injection from external messages.
  • Ingestion points: paw-mail emails body, paw-mail emails list, and paw-mail emails fetch commands in SKILL.md.
  • Boundary markers: None specified in the documentation.
  • Capability inventory: Execution of the paw-mail CLI and usage of Read, Glob, and Grep tools as specified in SKILL.md.
  • Sanitization: No explicit sanitization or filtering of email content is described.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 1, 2026, 09:39 PM