press-release-writing

Pass

Audited by Gen Agent Trust Hub on Sep 8, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs users to install a third-party package (belt-sh/cli) and references installation resources hosted on a third-party GitHub repository (inference-sh/skills).
  • [COMMAND_EXECUTION]: The skill utilizes a custom command-line interface (belt) to perform research queries and fact-check claims, executing commands through the Bash tool.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process information from external search engines to provide context for press release writing.
  • Ingestion points: External data is retrieved via the tavily/search-assistant and exa/search tools as described in SKILL.md.
  • Boundary markers: There are no identified delimiters or instructions to ignore potential commands embedded in the retrieved search data.
  • Capability inventory: The skill possesses the capability to execute shell commands to run research tools.
  • Sanitization: No sanitization or verification logic is present to filter external content before it is incorporated into the agent's workflow.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 8, 2026, 05:10 PM
Security Audit — agent-trust-hub — press-release-writing