skills/zexahq/post2all-agent/post2all/Gen Agent Trust Hub

post2all

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes the post2all CLI tool and npx @post2all/cli to perform social media management tasks such as creating, scheduling, and deleting posts.
  • [EXTERNAL_DOWNLOADS]: Fetches the @post2all/cli package from the npm registry using the npx command to ensure the tool is available for use.
  • [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes data from external social media APIs.
  • Ingestion points: Data retrieved from commands such as post2all accounts, post2all constraints, and post2all post get (found in SKILL.md).
  • Boundary markers: Absent. The skill does not define specific delimiters or instructions to ignore potential commands embedded in account metadata or post content.
  • Capability inventory: The skill can perform network operations via social media APIs and create or modify content across multiple platforms (LinkedIn, Instagram, TikTok, etc.).
  • Sanitization: Absent. There is no evidence of filtering or validation of the text data returned by external platforms before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 05:33 PM
Security Audit — agent-trust-hub — post2all