release-migration-analyzer
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external structured data (JSON/CSV), which serves as a potential entry point for indirect prompt injection if the data contains malicious instructions.
- Ingestion points: Data is read from a file path provided via the
--inputcommand-line argument inrun.py. - Boundary markers: No specific delimiters or safety instructions are currently implemented in the scaffold to isolate processed data from the agent's instructions.
- Capability inventory: The script in
run.pyusespathlibfor file system access (read and write) andjsonfor data parsing; no network or subprocess capabilities are present. - Sanitization: Input data is parsed as JSON but not otherwise sanitized or validated against a schema.
- [SAFE]: No malicious patterns such as obfuscation, hardcoded credentials, or remote code execution were found in the skill's instructions or implementation scripts.
Audit Metadata