external-reference-research

Pass

Audited by Gen Agent Trust Hub on Sep 23, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and synthesize information from untrusted external sources, creating a surface for indirect prompt injection.
  • Ingestion points: Data is retrieved via Web Search, GitHub Code Search, and Context7 (external library documentation) as described in the 'Tool Usage Strategy' section of SKILL.md.
  • Boundary markers: The instructions lack explicit delimiters or 'ignore' commands to prevent the agent from being influenced by malicious instructions embedded within the retrieved documentation or code samples.
  • Capability inventory: The skill uses GitHub CLI and Web Search for its operations, but does not include any local executable scripts or direct system command logic in the provided content.
  • Sanitization: There are no instructions for the agent to sanitize, escape, or filter the content retrieved from third-party repositories or websites before presenting it to the user or incorporating it into its reasoning processes.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 23, 2026, 08:05 AM
Security Audit — agent-trust-hub — external-reference-research