senpi-strategy-ops

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

• Third-party content exposure detected (low risk: 0.10). The workflow fetches external strategy package definitions via _fetch.py from a public GitHub repository (Senpi-ai/senpi-skills), which is an untrusted remote text/code source.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill fetches strategy packages dynamically from raw.githubusercontent.com and api.github.com at runtime without pinned digests or cryptographic verification, establishing a weak external dependency.