foundation-stakeholder-briefings
Pass
Audited by Gen Agent Trust Hub on Oct 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted source artifacts, which creates a potential surface for indirect prompt injection. (1) Ingestion points: Reads provided source artifacts like PRDs, research, and raw notes in SKILL.md Step 1. (2) Boundary markers: The output utilizes BEGIN/END delimiters for briefing blocks, but the skill lacks explicit instructions to ignore embedded commands within the ingested source material. (3) Capability inventory: The skill is restricted to text synthesis; it contains no subprocess calls, file system writes, or network operations. (4) Sanitization: No explicit sanitization or filtering of external content is implemented.
- [SAFE]: The skill is designed for document synthesis and audience tailoring. It does not request network access, execute arbitrary code, or access sensitive system files. All external references are to the author's own repositories and internal skill suite.
Audit Metadata