tamv-community-care
Pass
Audited by Gen Agent Trust Hub on Nov 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external, potentially untrusted content described as "Mensajes anonimizados y contexto".
- Ingestion points: Accepts external messages and context for processing as defined in SKILL.md.
- Boundary markers: Includes an explicit instruction to treat drafts as data, not as instructions, to prevent accidental execution of embedded content.
- Capability inventory: The skill generates responses and scales cases for review, transferring data to other internal governance modules.
- Sanitization: Requires the agent to minimize personal data and strictly avoid handling or sending secrets.
Audit Metadata