github-profile-research
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes content from external GitHub profiles, which could contain malicious instructions designed to influence agent behavior.\n
- Ingestion points: External data retrieved through the
strale_github_user_profiletool (referenced inSKILL.mdandreferences/sandbase-api-map.md).\n - Boundary markers: The instructions do not define boundary markers or explicit guidelines to ignore embedded instructions in the fetched data.\n
- Capability inventory: The skill uses the
sandbase_call_toolcapability for its operations.\n - Sanitization: There is no mention of sanitizing, validating, or filtering the content obtained from GitHub user profiles.
Audit Metadata