continuous-learning-v2
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of external pattern files which could harbor malicious instructions.
- Ingestion points: Untrusted content enters the agent's context through the
/instinct-importcommand described inSKILL.md. - Boundary markers: The skill does not implement delimiters or safety warnings to distinguish imported data from core system instructions.
- Capability inventory: Analysis of
SKILL.mdreveals no usage of dangerous tools such as subprocesses, file writing outside its scope, or network utilities. - Sanitization: There is no evidence of sanitization or validation logic for the content of imported patterns.
- [NO_CODE]: The skill consists entirely of natural language instructions and documentation without executable scripts or binaries.
Audit Metadata