inboundfy-conselho-marketing
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external project files (e.g.,
.inboundfy/context/empresa.md,.inboundfy/estrategia.md) which could contain untrusted data. - Ingestion points: Files located in the
.inboundfy/directory and referenced project documents. - Boundary markers: The skill uses structured templates for output but does not explicitly instruct the agent to ignore embedded instructions in the source files.
- Capability inventory: The skill only performs text transformations and file organization; it does not have access to shell execution, network operations, or privileged file system access.
- Sanitization: No explicit sanitization or escaping of input content is mentioned.
- [SAFE]: All identified external references and file paths are part of the internal project structure or the Inboundfy ecosystem managed by the vendor. No suspicious network activities, obfuscation, or credential exposures were found.
Audit Metadata