skill-from-github

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION] (LOW): The skill is susceptible to Indirect Prompt Injection (Category 8) because it ingests and processes untrusted data from external sources.
  • Ingestion points: The workflow involves reading README files, core source files, and documentation from any GitHub project selected by the user or agent (SKILL.md, Step 4).
  • Boundary markers: There are no explicit boundary markers or instructions to the agent to treat content within the GitHub projects as untrusted data or to ignore any embedded directives.
  • Capability inventory: While the skill itself primarily performs information gathering, its final step is to execute the /create-skill command (SKILL.md, Step 6), which creates new persistent instructions for the agent based on the extracted information.
  • Sanitization: No sanitization, filtering, or validation mechanisms are defined to ensure that instructions extracted from the GitHub project are safe or do not contain injection attempts.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:25 PM