data_analysis

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt includes hardcoded S3 credentials in the example (s3_access_key_id and s3_secret_access_key) and instructs constructing/printing scripts/commands that embed these values, which forces the agent to handle and potentially emit secret values verbatim.

HIGH W008: Secret detected in skill content (API keys, tokens, passwords).

• Secret detected (high risk: 1.00). The template contains two literal, high-entropy values set for S3/MinIO access: s3_access_key_id and s3_secret_access_key. These are not placeholders, truncated/redacted values, or simple setup passwords — they look like real credentials and therefore meet the secret definition. Although the doc notes they are "specific to the local dev environment," that does not make them placeholders under the rules, so they should be flagged.