article-prompts-to-skills

Pass

Audited by Gen Agent Trust Hub on Jul 28, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is designed to ingest untrusted external articles and prompt packs to generate new AgentSkill packages, which includes creating instructions and functional code demos. This workflow creates a surface for indirect prompt injection.\n
  • Ingestion points: The process involves reading external articles and tutorials as defined in SKILL.md (Step 1) and references/example-packages.md.\n
  • Boundary markers: No instructions are provided to use delimiters or boundary markers to isolate the external content from the agent's instructions.\n
  • Capability inventory: The skill utilizes powerful tools including Bash for shell access and Write/Edit for file modification.\n
  • Sanitization: There are no guidelines for sanitizing or validating the ingested content before it is used to generate new skill components.\n- [COMMAND_EXECUTION]: The instructions (Step 4 and Step 7) direct the agent to execute external utility scripts, specifically a skill-creator initializer and quick_validate.py. While presented as part of the intended environment, these are external dependencies that are executed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 28, 2026, 03:02 AM
Security Audit — agent-trust-hub — article-prompts-to-skills