pig-expert

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). The skill's workflow and reference docs (e.g., references/aws-emr.md, references/gcp-dataproc.md, references/udfs.md, and references/input-output.md) explicitly show loading/registering Pig scripts and UDF jars from s3:// and gs:// locations (e.g., "--file=gs://my-bucket/scripts/myscript.pig", "REGISTER 's3://bucket/libs/myudfs.jar'"), which requires ingesting user-controlled third‑party content that can materially change execution and tool behavior.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill contains explicit runtime commands that fetch and load remote code (e.g., REGISTER 's3://my-bucket/libs/piggybank-0.17.0.jar' and initialization actions like gs://my-bucket/init-actions/setup_pig_libs.sh), which are pulled at job/cluster runtime and execute as UDFs or setup scripts, so this is a runtime external dependency that can execute remote code.