cold-email-reply-scoring
Pass
Audited by Gen Agent Trust Hub on Sep 8, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the
Bashtool to execute a local script (scripts/score_reply.py) for processing email data batches.- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted data from external email responses (replies.jsonl). Although the classification logic is deterministic, the processing of external text presents a potential surface for indirect prompt injection that could affect downstream tasks performed by the agent.
Audit Metadata