heap-snapshot-analysis

Pass

Audited by Gen Agent Trust Hub on Apr 21, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • Local Script Execution: The skill encourages the creation and execution of specialized analysis scripts within a local scratchpad directory. This allows for flexible, task-specific memory investigations while utilizing the provided TypeScript helpers.
  • Context Management Instructions: The skill includes instructions for the agent to disregard prior investigation results. This is intended to ensure that new analyses are not biased by outdated information or previous session data.
  • Data Ingestion Analysis: The skill processes user-supplied V8 heap snapshot files. 1. Ingestion points: parseSnapshot.ts reads snapshots from specified file paths. 2. Boundary markers: No explicit delimiters are used for the snapshot data. 3. Capability inventory: The skill has file system read access and the ability to execute Node.js scripts. 4. Sanitization: The parser extracts specific JSON segments using buffer offsets to manage data safely.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 21, 2026, 02:52 PM