inboundfy-especialista-ebook-imagem
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 project data from several local markdown and configuration files, creating a surface for instructions embedded in those files to influence agent behavior.\n
- Ingestion points: The skill reads project-specific configuration and context files, including
context/canais.md,context/marca-voz.md,context/glossario.md, and.inboundfy/setup files as specified inSKILL.md.\n - Boundary markers: There are no explicit instructions or delimiters defined to separate or ignore potential command-like instructions within the ingested project files.\n
- Capability inventory: The skill's capabilities are restricted to file system read/write operations and the invocation of other internal framework skills (
inboundfy-base-imagem,inboundfy-validador-ebook-imagem). It does not utilize network operations or arbitrary command execution.\n - Sanitization: No sanitization, escaping, or validation logic is defined for the content extracted from the project files before it is used to generate image briefs or perform validation checks.
Audit Metadata