github-actions-trigger

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The prompt includes a ghp_* token example and explicitly instructs saving gh_token into context-memory while showing code that inserts that token verbatim into Authorization headers, which requires the agent to handle and could cause it to output secrets directly.

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly calls GitHub's public API (see API Functions: get_runs and get_logs against https://api.github.com) and its Pre-built Integration Flows instruct the agent to read run outputs (e.g., "Get deployment URL", "Monitor status every 30s" and "Report pass/fail"), meaning untrusted, user-generated repository workflow logs and outputs are ingested and can materially influence actions.