agent-memory
Pass
Audited by Gen Agent Trust Hub on Mar 22, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill uses local files to coordinate state, which creates a vulnerability to indirect prompt injection.
- Ingestion points: The agent is instructed to read
MEMORY.md,tasks.json, and files within theprojects/directory at the start of every session. - Boundary markers: There are no delimiters or specific instructions provided to distinguish between the agent's core instructions and the data contained within the memory files.
- Capability inventory: The skill enables the agent to write to and modify files in the project directory, and the agent typically has broader execution permissions.
- Sanitization: No sanitization or verification of the file content is performed before it is added to the agent's context.
Audit Metadata