dyno-run-debug

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.80). The skill tells the agent to extract and include log lines and recovered artifact contents (via jq and in the "Key evidence" report), which can contain API keys or secrets and therefore may force the LLM to output secret values verbatim.

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

• Third-party content exposure detected (high risk: 0.70). The required workflow ingests the user-pasted Dynobox run output (a free-form text block) into the dyno-run-debug scenario prompt (see dyno/fixtures/dyno-run-debug.dyno.mjs where the prompt includes “The user pasted this debug output” and then the pasted output is embedded), which is outsider-authored content if the operating user did not author it.