inboundfy-contexto-marca
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest untrusted data from users, such as examples of "good" or "bad" brand voice, and write them into persistent storage (
context/marca-voz.md,context/proibicoes.md). - Ingestion points: User-provided text snippets and editorial examples in
SKILL.md(Fluxo step 3). - Boundary markers: The skill does not define specific sanitization or boundary markers for user-supplied examples written to the Markdown files.
- Capability inventory: The skill possesses read and write capabilities for project-level Markdown files which are then consumed by other agents in the framework (e.g.,
inboundfy-copy-editor). - Sanitization: There is no evidence of filtering or escaping for user-supplied content before it is stored in the context files, which could allow a user to inject instructions that influence downstream agents.
Audit Metadata