github-profile
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill fetches external data from the GitHub API (user bio and repository descriptions) which is then used to generate a profile README. This represents a potential surface for indirect prompt injection if the external data contains malicious instructions.\n
- Ingestion points: The
SKILL.mdfile describes usinggh apito collect profile information in Phase 0.\n - Boundary markers: The instructions do not define specific delimiters for separating untrusted data from the agent's instructions.\n
- Capability inventory: The skill's primary capabilities are fetching data via API and generating markdown content.\n
- Sanitization: There are no explicit validation or sanitization steps defined for the fetched data.\n- [SAFE]: The skill correctly instructs users to use GitHub Secrets for storing Personal Access Tokens (PATs), which is a standard security best practice.
Audit Metadata