two-tier-extraction
Pass
Audited by Gen Agent Trust Hub on Aug 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes large volumes of untrusted third-party content, such as email archives and document dumps, which creates a surface for indirect prompt injection attacks.
- Ingestion points: Bulk content is ingested from external archives as described in
SKILL.md. - Boundary markers: The skill implements a mechanism to flag detected imperatives (instructions) within the data using the
untrusted_directives: trueflag and dedicated markdown fences, ensuring they are not obeyed by the agent. - Capability inventory: The skill has permissions to write to various local directories (
originals/,personal/,people/,companies/,sources/) and is marked asmutating: true. - Sanitization: The skill includes a 'Privacy Wall' that uses deterministic regex and exact-match rules to strip sensitive patterns (credentials, medical terms, legal terms) and private contacts from the data before it is sent to any LLM.
Audit Metadata