snapas

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.80). The skill's examples and guidance require inserting Write.as access tokens directly into Authorization headers and curl commands (e.g., -H "Authorization: Token ..."), so an LLM generating real requests would need to include secret token values verbatim, creating exfiltration risk.

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

• Third-party content exposure detected (high risk: 1.00). The skill includes calls to the public Snap.as API (e.g., endpoints like https://snap.as/api/me/photos and public image URLs such as https://i.snap.as/abc123.jpg) and instructs retrieving and displaying user-uploaded photos/metadata, which are untrusted third-party user-generated content the agent would read as part of its workflow.