loops-api
Pass
Audited by Gen Agent Trust Hub on Nov 10, 2026
Risk Level: SAFECREDENTIALS_UNSAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is a legitimate documentation resource for the Loops platform. All external URLs (e.g., loops.so, app.loops.so) and software packages (e.g., loops, nuxt-loops, loops_sdk) are verified vendor resources originating from the skill author, loops-so.
- [CREDENTIALS_SAFE]: The reference material explicitly instructs users not to hardcode API keys in source code and to use environment variables or secret managers, reflecting standard security best practices.
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of data from external sources, specifically through API responses and inbound webhooks.
- Ingestion points: Code examples show parsing of JSON payloads from webhooks and API calls in references/http-api.md.
- Boundary markers: No explicit delimiters or instructions for the agent to ignore embedded commands are present in the provided templates.
- Capability inventory: The skill includes the capability to perform network requests using the official vendor API endpoint.
- Sanitization: The implementation guides demonstrate standard property extraction but do not emphasize sanitization of inputs from external sources.
Audit Metadata