session-artifact-indexing

Pass

Audited by Gen Agent Trust Hub on Aug 14, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [DYNAMIC_EXECUTION]: The skill generates AppleScript files at runtime and executes them via osascript to interact with Apple Notes.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes session artifacts such as documents and links. 1. Ingestion points: Multi-step session artifacts and files. 2. Boundary markers: None. 3. Capability inventory: osascript, bash, and memo CLI tool. 4. Sanitization: The instructions recommend writing script files to mitigate shell injection risks associated with ampersands in command strings.
  • [DATA_EXPOSURE_AND_EXFILTRATION]: The skill creates indices containing local file paths (file://), which records the user's file system structure in a durable note format.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 14, 2026, 07:56 AM
Security Audit — agent-trust-hub — session-artifact-indexing