agent-tools

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (low risk: 0.10). The skill includes search and social tools (Tavily, Exa, Twitter) that can ingest external free text when invoked, representing low-risk indirect prompt injection exposure via fetched content.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs installation of external binaries via curl -fsSL https://cli.inference.sh | sh, representing an unverified runtime external dependency with high risk.