openpost-cli

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the openpost CLI to interact with an OpenPost instance. It includes instructions to verify command availability and prohibits installation of external software without user consent.
  • [INDIRECT_PROMPT_INJECTION]: The skill interacts with external data which can contain malicious instructions.
  • Ingestion points: The skill ingests data via openpost publication comments and local Markdown thread files (references/workflows.md).
  • Capability inventory: The agent can perform sensitive actions such as publishing content, deleting publications, and moderating comments (hide, delete, reply) via the CLI.
  • Boundary markers: The skill requires user confirmation for mutations but does not define explicit delimiters or 'ignore' instructions for the external data it processes.
  • Sanitization: There is no evidence of sanitization or filtering for data retrieved from third-party social media providers before it is used in automation.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 05:15 PM
Security Audit — agent-trust-hub — openpost-cli