memory-leak-debugging
Pass
Audited by Gen Agent Trust Hub on Apr 3, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill uses
npx memlabto perform memory leak analysis.memlabis a well-known open-source tool maintained by Meta (Facebook) for heap analysis. - [COMMAND_EXECUTION]: The skill executes a local Node.js script (
references/compare_snapshots.js) and thememlabCLI vianpx. These commands are used to process memory snapshots provided by the user. - [PROMPT_INJECTION]: The skill processes
.heapsnapshotfiles, which are external data sources that could potentially contain malicious instructions intended to influence the agent. - Ingestion points: The script
references/compare_snapshots.jsparses and prints object names and types directly from heap snapshot files. - Boundary markers: Output from the analysis script is presented to the agent without delimiters or instructions to ignore embedded content.
- Capability inventory: The agent has access to shell execution (
node,npx) and browser control tools (chrome-devtools-mcp). - Sanitization: There is no sanitization or escaping of the strings extracted from the heap snapshots before they are processed by the agent.
Audit Metadata