agentos-api-memory
Pass
Audited by Gen Agent Trust Hub on Mar 26, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is a legitimate API client implementation designed to manage user-specific data on an AgentOS instance. Its behavior aligns with its stated purpose.- [EXTERNAL_DOWNLOADS]: The management script 'scripts/manage_memories.py' depends on the 'agno' package, which is the official library for the AgentOS platform described in the skill. Dependencies are managed using standard Python package management conventions.- [COMMAND_EXECUTION]: The CLI tool 'scripts/manage_memories.py' implements safe argument parsing using the 'argparse' module. It does not use any dangerous functions like 'eval()' or 'os.system()' to process user-supplied input.- [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it retrieves and processes user-controlled data from a remote API. Evidence: (1) Ingestion points: The 'list_memories' and 'get_memory' calls in 'scripts/manage_memories.py' fetch memory content. (2) Boundary markers: No delimiters or protective instructions are used to wrap the memory content when it is displayed or returned to the agent. (3) Capability inventory: The skill is restricted to API network operations and terminal output. (4) Sanitization: No content validation or escaping is performed on the data retrieved from the API.
Audit Metadata