tamv-core-governance
Pass
Audited by Gen Agent Trust Hub on Nov 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill requires 'datos de usuario' (user data) as input, creating a surface where malicious instructions could be embedded in the processed data.
- Ingestion points: SKILL.md identifies 'datos de usuario' as a required input field.
- Boundary markers: The skill does not define specific delimiters (like XML tags or triple quotes) to isolate user data from its internal instructions.
- Capability inventory: The skill is designed to guide the agent in generating architectures, implementation plans, and decision-making; while the skill itself does not call external tools in this file, the resulting agent output could be compromised by malicious input.
- Sanitization: There are no instructions provided to sanitize, escape, or validate the user-supplied data before processing.
Audit Metadata