memorb-lint
Pass
Audited by Gen Agent Trust Hub on Aug 10, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface because it is designed to ingest and process content from external markdown files that could potentially contain adversarial instructions.
- Ingestion points: The skill reads
memorbs/MEMORY.md,memorbs/log.md, and random pages within thememorbs/directory (SKILL.md). - Boundary markers: There are no explicit delimiters or instructions provided to the agent to ignore or neutralize instructions embedded within the memory files it processes.
- Capability inventory: The skill has the capability to read/write local files (
log.md) and suggest the execution of another tool (memorb-forgetter). - Sanitization: No sanitization or validation logic is defined for the content retrieved from the markdown pages before processing.
Audit Metadata