briefing-outline
Pass
Audited by Gen Agent Trust Hub on Sep 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted user-provided documents and reports, which creates a surface for indirect prompt injection attacks.
- Ingestion points: The skill ingests "one long report or multiple source documents" as specified in SKILL.md.
- Boundary markers: The instructions do not define explicit delimiters or "ignore" warnings to isolate untrusted source content from the agent's primary instructions.
- Capability inventory: The skill does not possess dangerous capabilities such as file system writing, network operations, or subprocess execution.
- Sanitization: No input sanitization or filtering is performed on the ingested content.
- [EXTERNAL_DOWNLOADS]: The skill's documentation (guide.en.md and guide.zh.md) provides installation commands referencing the author's official GitHub repository (github.com/leoluyi/skills), which is a vendor-owned resource.
Audit Metadata