airbnb-listing-detail

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

• Third-party content exposure detected (medium risk: 0.30). At runtime the skill’s scripts/listing-detail.py builds and executes a fetch() call to Airbnb’s StaysPdpSections endpoint and parses free-form listing fields (e.g., title, description, amenities, house_rules, highlights) from the API response, which could include outsider-authored content (host/guest text) for any listing ID the user chooses.

HIGH W008: Secret detected in skill content (API keys, tokens, passwords).

• Secret detected (high risk: 1.00). I flagged the hardcoded API key in scripts/listing-detail.py because it is a high-entropy, literal value used in an HTTP header ('X-Airbnb-API-Key') and therefore appears to be a real credential that could grant API access. Other high-entropy-looking values were reviewed and not flagged: the persistedQuery sha256Hash is an identifier/hash (not an access credential), and the base64-encoded strings are derived from the listing ID (not secrets). Trivial/static header values like '1' or 'true' are not secrets.