klh-openapi-directory-first

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

• Third-party content exposure detected (high risk: 0.95). The required workflow fetches OpenAPI specs from the public GitHub repository APIs-guru/openapi-directory via raw URLs (e.g., raw.githubusercontent.com/.../openapi.yaml), which is outsider-authored free text (public web content) ingested into the agent’s LLM context.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly instructs fetching OpenAPI specs at runtime (e.g., https://raw.githubusercontent.com/APIs-guru/openapi-directory/main/APIs/{provider.com}/{version}/openapi.yaml, the GitHub API curl in Step 1, and https://api.apis.guru/v2/list.json) and using those fetched specs to drive agent behavior, so external content would directly control prompts/instructions.