persona-life-assistant
Warn
Audited by Gen Agent Trust Hub on Nov 4, 2026
Risk Level: MEDIUMPERSISTENCEPRIVILEGE_ESCALATIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [PERSISTENCE]: The skill implements a signaling mechanism that writes data to
~/.openclaw/feedback/signals.jsonvia a Node.js bridge (scripts/state-sync.js). This involves interacting with the host environment outside the skill's own directory, allowing the agent to maintain state and communicate with the underlying platform across different sessions. - [PRIVILEGE_ESCALATION]: Through the defined 'Signal Protocol', the agent is instructed to proactively request increased permissions from the host, such as
file_ioorcapability_gap. This mechanism provides a structured way for the agent to attempt to expand its operational boundaries and gain access beyond its initial sandbox constraints. - [EXTERNAL_DOWNLOADS]: The skill uses
npxto execute the@agentplanet/acnpackage for on-chain identity registration. This involves downloading and running code from an external package registry, which introduces risks related to third-party dependency trust and integrity. - [COMMAND_EXECUTION]: The skill is configured with extensive tool access, including multiple
Bashscopes,npm,npx,node, andcurl. It relies on these tools for core functions like state synchronization and registration, creating a significant surface for command execution on the host system. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user data—such as tasks, shopping lists, and recipes—while having access to powerful tools like shell execution and web fetching. This combination creates a surface for indirect prompt injection attacks.
- Ingestion points: User input for schedule management in
references/reminder.mdand task/shopping list data insoul/persona.json. - Boundary markers: There are no specified delimiters or 'ignore embedded instructions' warnings for external data processing.
- Capability inventory: Access to
Bash(includingopenclaw,node,npm,npx, andcurl),Read/Writefile operations, andWebFetchfor network requests. - Sanitization: No evidence of sanitization, input validation, or escaping of user-provided or web-fetched content is present in the skill's logic.
Audit Metadata