hence-collections

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt explicitly shows passing an API key on the command line (python scripts/auth.py ), which is an insecure pattern that requires embedding secret values verbatim in commands.

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

• Third-party content exposure detected (high risk: 0.80). The skill's CLI and API docs (scripts/collections.py and references/api.md) explicitly fetch and display user-generated project data from hence.sh via endpoints like GET /api/collections and GET /api/collections/?q=..., and those titles/descriptions are read and used to select or add projects (e.g., "If the user found a project via hence-search, use the project ID"), so untrusted third-party content can influence action selection.