skills/daxaur/openpaw/c-notes/Gen Agent Trust Hub

c-notes

Pass

Audited by Gen Agent Trust Hub on Mar 9, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes the local CLI commands memo and remindctl to interact with macOS native applications. These tools allow the agent to read, create, search, and delete user data.
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it ingests content from external sources (Apple Notes and Reminders) that could be controlled by an attacker.
  • Ingestion points: Data enters the agent's context through the memo read, memo search, and remindctl list commands as described in SKILL.md.
  • Boundary markers: There are no markers or delimiters defined to isolate the retrieved content from the agent's instructions, nor are there instructions to ignore embedded commands.
  • Capability inventory: The skill possesses the ability to modify the local state by creating or deleting notes and reminders via subprocess calls to CLI tools.
  • Sanitization: The skill does not perform any validation or sanitization of the data retrieved from the local applications before processing it.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 9, 2026, 08:44 AM
Security Audit — agent-trust-hub — c-notes