op-cli

Pass

Audited by Gen Agent Trust Hub on Aug 26, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill implements management of OpenProject resources by executing the op-cli command-line utility for operations like work package manipulation and time logging.
  • [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it retrieves and processes content from an external OpenProject instance.
  • Ingestion points: Content is ingested from the OpenProject instance via commands like op-cli wp list and op-cli wp get described in SKILL.md.
  • Boundary markers: While the skill includes instructions to avoid bypassing the CLI or reading credentials.json, it does not provide specific instructions to the agent regarding the handling of potentially malicious instructions within work package data.
  • Capability inventory: Through op-cli, the agent can create, modify, and delete work packages, projects, and time entries, and perform tool updates.
  • Sanitization: No specific data sanitization steps are defined for the input received from the CLI commands.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 26, 2026, 06:46 AM
Security Audit — agent-trust-hub — op-cli