bm-orient
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from a memory graph that may contain untrusted content intended to influence agent behavior.
- Ingestion points: Content is retrieved from the memory graph via the
search_notesandread_notetools as described in SKILL.md. - Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions to isolate retrieved content from the agent's primary task instructions.
- Capability inventory: While this skill is read-oriented, the agent environment typically includes tool access for file system operations and command execution.
- Sanitization: No validation, filtering, or sanitization of the retrieved note content is performed before presenting it to the agent.
Audit Metadata