performance-monitor-analyst
Pass
Audited by Gen Agent Trust Hub on Mar 5, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes external JSON and JSONL files through the
inputargument, parsing their content and incorporating fields like theskillname directly into the output report. This creates a surface for indirect prompt injection, where an attacker could place malicious instructions inside a metrics file to influence the agent when it reads the report. - Ingestion points: The
inputCLI argument insrc/index.tsdefines the file paths read viafs.readFileSyncandfs.readdirSync. - Boundary markers: The generated report does not use specific delimiters or instructions to the AI to ignore content within the metrics data.
- Capability inventory: The skill can read any file the process has access to (
fs.readFileSync) and can write files to arbitrary paths via theoutargument (safeWriteFile). - Sanitization: The skill performs no validation or sanitization on the strings extracted from JSON/JSONL metrics before including them in the final report.
Audit Metadata