memory-management
Pass
Audited by Gen Agent Trust Hub on Mar 30, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill creates a surface for indirect prompt injection by storing data from external sources (such as keyword research and competitor analysis) into CLAUDE.md, which is a file frequently loaded into the agent's active context. If external data contains malicious instructions, they could influence the agent's behavior in subsequent sessions.
- Ingestion points: The skill ingests data from external SEO tools, search console, and analytics platforms into CLAUDE.md and the memory/ directory.
- Boundary markers: The skill uses markdown headers and tables for organization but does not implement explicit delimiters or 'ignore' instructions for the data being stored.
- Capability inventory: The skill is designed to perform file system read and write operations within the project directory to manage memory state.
- Sanitization: No sanitization, validation, or filtering of the ingested external data is mentioned in the instructions.
Audit Metadata