skills/onevcat/prowl/prowl-cli/Gen Agent Trust Hub

prowl-cli

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the prowl CLI tool and jq utility to perform operations such as listing panes, reading agent states, and sending commands to sibling processes. These operations are restricted to the local environment and the application's own context.
  • [INDIRECT_PROMPT_INJECTION]: The skill defines a surface for processing data from external agent sessions, which is inherent to its purpose of session management. \n
  • Ingestion points: External agent data enters the context via prowl agents read, prowl read, and prowl list (SKILL.md). \n
  • Boundary markers: The skill documentation explicitly recommends the use of the --json flag and jq for structured parsing to ensure that agent output is treated as data rather than instructions. \n
  • Capability inventory: The skill has the ability to send text and keys to other panes via prowl send and prowl key (SKILL.md). \n
  • Sanitization: The skill advises using shell variable quoting (via jq --arg and single quotes for payloads) and identity verification using $PROWL_PANE_ID to minimize risks of acting on incorrect or unverified context.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 01:34 PM
Security Audit — agent-trust-hub — prowl-cli