bm-remember
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the user and persists it into a memory store, creating a potential surface for indirect prompt injection if that data is later retrieved and executed as instructions.
- Ingestion points: User-provided text passed through the
$ARGUMENTSvariable inSKILL.md. - Boundary markers: The skill does not define specific delimiters or "ignore instructions" warnings for the content being saved.
- Capability inventory: The skill uses the
write_notetool to save content to the filesystem or a connected memory service. - Sanitization: No explicit sanitization or validation of the input text is performed before it is passed to the storage tool.
Audit Metadata