env-secrets-manager

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

• Third-party content exposure detected (high risk: 0.70). The skill's documentation explicitly instructs querying public GitHub (e.g., "gh api search/code -f q='THE_LEAKED_VALUE'" and "gh pr list/gh pr diff") in the "Credential Rotation Workflow" section of SKILL.md, which causes the agent to fetch and interpret user-generated, untrusted third-party content that can affect subsequent remediation actions.