skillshare

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

• Third-party content exposure detected (high risk: 0.75). Outsider-authored free text can enter the LLM context via skillshare install/update/search workflows that fetch and ingest README/SKILL.md/content from remote git repos or public web sources at runtime (e.g., user/repo or https://...), which are not authored by the operating user.

MEDIUM W013: Attempt to modify system services in skill instructions.

• Attempt to modify system services in skill instructions detected (medium risk: 0.60). The skill instructs the agent to install and sync arbitrary repos into user config directories (modifying local machine state) and explicitly provides flags (--force, --skip-audit) to bypass the security audit, though it does not request sudo or modify system-level files or create users.