broll-assets

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The line "only an exact Pexels request receives its credential" instructs embedding a credential into a request (i.e., including a secret in generated output), which requires the LLM to handle and output secret values verbatim and therefore is a high exfiltration risk.

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

• Third-party content exposure detected (low risk: 0.10). The required runtime workflow in SKILL.md states it inspects user-supplied material and then freezes only selected assets (including optional Pexels), but it does not describe ingesting arbitrary outsider-authored free text from external feeds/queues (e.g., email, chat, issues, tickets) without the agent selecting a specific item first.