inboundfy-especialista-newsletter
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted input from external brief files to generate newsletter content, creating a potential surface for indirect instructions to influence the agent.\n
- Ingestion points: Reads files such as
acervo/<id>-<data>-<slug>/base-editorial.mdand user-provided briefs as part of its core workflow inSKILL.md.\n - Boundary markers: There are no explicit delimiters or instructions to ignore embedded commands within the ingested brief content.\n
- Capability inventory: The skill possesses capabilities to read and write to the local file system and trigger other agent tools/skills (e.g.,
inboundfy-validador-newsletter).\n - Sanitization: The instructions do not specify any sanitization or validation of the brief's text content before it is used for generation.
Audit Metadata