resolve-open-loops
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes memory items retrieved via the
memory_searchtool, which constitutes a surface for indirect prompt injection if those memories contain malicious instructions intended to manipulate the agent's behavior during triage. - Ingestion points: Content is retrieved from the
Lorememory system via thememory_searchtool as specified inSKILL.md(Retrieval workflow steps 1 and 3) andreferences/memory-types.md. - Boundary markers: The instructions do not define specific delimiters or "ignore embedded instructions" warnings for the memory content, although the workflow suggests presenting only the first 120 characters as a summary.
- Capability inventory: The skill has the capability to modify the persistent memory state through the
memory_forgetandmemory_savetools. - Sanitization: No explicit sanitization or validation of the retrieved memory content is performed beyond the truncation for summary display.
Audit Metadata