The Agent Skills Directory

[SAFE]: Secret Management: The skill demonstrates secure practices in SKILL.md by instructing the agent to use environment variables (APIDECK_API_KEY, APIDECK_APP_ID) for authentication tokens, avoiding hardcoded secrets.- [SAFE]: Trusted Infrastructure: All network communications, documentation links, and resource references in SKILL.md and metadata.json target official domains belonging to Apideck and eBay. No suspicious external dependencies or typosquatted domains were detected.- [INDIRECT_PROMPT_INJECTION]: Data Ingestion Surface: The skill enables the agent to fetch data from external eBay resources (such as orders and products), which constitutes a surface for indirect prompt injection if the data contains malicious instructions.
Ingestion points: SKILL.md (retrieval of Ecommerce data via Apideck unified API).
Boundary markers: None specified in the instructions to separate untrusted data from agent instructions.
Capability inventory: SKILL.md (Network operations via SDK and curl to Apideck's API).
Sanitization: No sanitization or validation steps for incoming data are described in the instructions.

ebay