inboundfy-especialista-podcast
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructions direct the agent to utilize several command-line tools or specialized skills from the same vendor (e.g.,
inboundfy-setup,inboundfy-copy-editor,inboundfy-validador-podcast) to manage project preparation and content quality control. - [INDIRECT_PROMPT_INJECTION]: The skill ingests external data (episode briefs) to produce generated content, which creates a potential surface for indirect prompt injection if the input contains malicious instructions designed to alter the agent's behavior.
- Ingestion points: Input briefs containing episode themes and objectives (SKILL.md).
- Boundary markers: There are no explicit delimiters or instructions provided to separate the external brief content from the core logic.
- Capability inventory: The skill is capable of performing file system write operations to save generated artifacts (SKILL.md).
- Sanitization: No explicit content sanitization or validation logic is defined for the input data.
Audit Metadata