The Agent Skills Directory

[SAFE]: The skill uses environment variables (SENTISENSE_API_KEY) for authentication, which is a standard and secure method for managing API credentials without hardcoding secrets.
[SAFE]: All network activity is restricted to the vendor's official API domain (sentisense.ai), and the skill is limited to read-only operations, preventing unauthorized financial transactions or system modifications.
[INDIRECT_PROMPT_INJECTION]: The skill ingests AI-generated markdown summaries from an external source, creating a potential surface for indirect prompt injection.
Ingestion points: Data is retrieved from the earnings-summaries and insights endpoints described in SKILL.md.
Boundary markers: The skill includes a 'Use and disclaimer' section that explicitly directs the agent to treat API content as data to report, never as instructions to follow.
Capability inventory: The agent's capabilities are restricted to performing GET requests to a specific set of vendor endpoints; no file-writing, command execution, or other high-privilege operations are permitted.
Sanitization: The skill provides specific Output Laws and derived classification logic (e.g., for guidance direction) to ensure the agent interprets and reports the data strictly as intended.

stock-earnings-analysis