inboundfy-especialista-substack
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from briefs and content collections to generate articles, creating a vulnerability surface for indirect prompt injection. 1. Ingestion points: Data is read from acervo (collections) and brief.md files. 2. Boundary markers: The instructions do not provide explicit delimiters or warnings to isolate untrusted content. 3. Capability inventory: The skill is instructed to write and modify files in the canais/substack/ directory. 4. Sanitization: No validation or filtering of the input content is described.
Audit Metadata