title-generator

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

• Third-party content exposure detected (high risk: 0.80). This skill directly consumes arbitrary user-provided or piped text via stdin or the --input flag (see scripts/run.sh and scripts/_generate.py) and then parses that untrusted content to extract keywords and generate titles, so external/user-generated content can influence the agent's behavior.