inboundfy-concorrentes
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 data from competitor websites and project artifacts, creating a potential attack surface for indirect prompt injection.
- Ingestion points: Competitor URLs and names provided as input in
SKILL.md, and processed data files within theacervo/directory as described inREFERENCIA.md. - Boundary markers: Absent. The skill instructions do not define specific delimiters or isolation techniques to separate untrusted external content from the agent's internal instructions.
- Capability inventory: The skill performs file read and write operations within the project workspace, specifically inside the
.inboundfy/andacervo/directories. - Sanitization: The instructions include qualitative validation steps (e.g., separating facts from interpretation, ensuring no defamation, and verifying that advantages are not invented) but do not specify technical sanitization or input filtering.
Audit Metadata