inboundfy-especialista-linkedin
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 external data from marketing briefs and various project configuration files located in the 'context/' directory (e.g., 'context/pessoas.md', 'context/publico.md').
- Ingestion points: Data enters the agent's context through user-provided briefs and local project files referenced in SKILL.md and REFERENCIA.md.
- Boundary markers: The instructions do not define clear delimiters or include warnings for the agent to ignore instructions embedded within the processed data, which could lead to accidental execution of commands hidden in the input.
- Capability inventory: The skill has the capability to read files, write generated content to specific paths, and invoke other skills in the pipeline (e.g., 'inboundfy-copy-editor', 'inboundfy-validador-linkedin').
- Sanitization: There is no evidence of sanitization or filtering of external content before it is interpolated into the agent's prompt context.
Audit Metadata