inboundfy-aso
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from project-specific files and user inputs, creating a surface for potential instruction injection from external sources.\n
- Ingestion points: Context files located in the .inboundfy/context/ directory and user-provided content via acervo IDs as described in the workflow.\n
- Boundary markers: The skill uses structured templates and YAML frontmatter to delimit data and instructions, reducing the risk of accidental instruction execution.\n
- Capability inventory: The skill is limited to reading local context files and generating text artifacts; no network access or shell command execution capabilities are present in the scripts or instructions.\n
- Sanitization: The workflow incorporates explicit validation steps and references review skills such as inboundfy-anti-slop and inboundfy-copy-edicao to filter generated content.\n- [SAFE]: All identified external references and directory structures (e.g., .inboundfy/) belong to the vendor ecosystem and represent standard operational behavior for this skill type.
Audit Metadata