lolipop-deploy
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches deployment procedures and supplementary service information from the official Lolipop website (lolipop.jp) at runtime to ensure the agent uses current instructions.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and follow instructions from external URLs (https://lolipop.jp/ai/skills/skill.md), which creates a surface for indirect prompt injection if the remote content were to contain adversarial directives.
- Ingestion points: SKILL.md (retrieves data from lolipop.jp)
- Boundary markers: Absent; instructions are fetched and followed without explicit delimiters or ignore-instructions warnings.
- Capability inventory: Mentions SSH-based deployment and file operations (rsync).
- Sanitization: Absent; the skill directs the agent to return the full content of the fetched file without validation.
Audit Metadata