press-release-writing

Pass

Audited by Gen Agent Trust Hub on Apr 14, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: References the installation of the inference.sh CLI tool and additional skill modules from the inference-sh GitHub repository.
  • [COMMAND_EXECUTION]: Instructs the agent to use the infsh command-line utility to run research applications such as tavily/search-assistant and exa/search.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface (Category 8) by ingesting untrusted data from external web searches to inform its writing process.
  • Ingestion points: External search results retrieved via the infsh CLI tools (SKILL.md).
  • Boundary markers: Absent; there are no specific delimiters or instructions provided to the agent to ignore or isolate potential instructions embedded in the search results.
  • Capability inventory: Execution of the infsh CLI tool for research and fact-checking (SKILL.md).
  • Sanitization: Absent; the skill does not specify methods for validating or filtering the retrieved data before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 14, 2026, 11:25 PM